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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8594
    Prev
    Next
    INDEX
    Explanations

    expressions indicating authority or control

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

    personal pronouns in emphatic or declarative contexts (statements about oneself or others using "I'm," "you are," "he's," "she's").

    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
     ſtate
    -0.70
     ſta
    -0.66
     Reſ
    -0.65
    Попис
    -0.65
    EndProject
    -0.65
    aarrggbb
    -0.64
    styleType
    -0.63
    IsMutable
    -0.63
    mybatisplus
    -0.62
     itſelf
    -0.62
    POSITIVE LOGITS
     gonna
    0.59
     afraid
    0.51
     tired
    0.50
     kidding
    0.47
     ashamed
    0.46
     smarter
    0.44
     supposed
    0.44
     cool
    0.43
     embarrassed
    0.43
     different
    0.43
    Activations Density 0.356%

    No Known Activations