© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13587
    Prev
    Next
    INDEX
    Explanations

    sentences that relate to consequences or conditions regarding actions and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discourse and sentence-transition cues—contrast/continuation connectives and nearby sentence-ending punctuation.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    punctuation and words that indicate sentence boundaries or transitions.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    sentence-ending punctuation marks and discourse connectors that signal transitions between clauses or ideas.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nghề
    -0.56
    Ссылки
    -0.54
     Relacion
    -0.51
     coute
    -0.50
    دانشنامهٔ
    -0.50
     laget
    -0.50
    мужские
    -0.49
     AppColors
    -0.47
     Chriſt
    -0.47
     Diſ
    -0.47
    POSITIVE LOGITS
     mergeFrom
    0.86
     InputDecoration
    0.83
    RenderAtEndOf
    0.78
     CreateTagHelper
    0.77
    出版年
    0.74
     <=",
    0.70
     BorderRadius
    0.70
     ModelExpression
    0.70
     NgModule
    0.68
     ویکی‌پدی
    0.66
    Activations Density 0.483%

    No Known Activations