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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3531
    Prev
    Next
    INDEX
    Explanations

    references to published articles and research discussions

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

    words related to published articles, stories, and written works.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ffilmiau
    -0.61
     autorytatywna
    -0.59
    AndEndTag
    -0.57
    MergeFrom
    -0.54
    AnchorStyles
    -0.52
    лтамалар
    -0.49
     ब्रेकडाउन
    -0.49
    AnimationsModule
    -0.48
    RenderAtEndOf
    -0.46
     kasarigan
    -0.46
    POSITIVE LOGITS
     published
    1.74
    published
    1.45
     publish
    1.38
     publication
    1.35
     publicado
    1.30
     appearing
    1.29
    Published
    1.28
     Published
    1.28
     appeared
    1.27
     publicada
    1.27
    Activations Density 0.456%

    No Known Activations