Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7935
    Prev
    Next
    INDEX
    Explanations

    references to societal beliefs and values related to race and inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.89
    BufferException
    -0.71
    Бележки
    -0.69
     ویکی‌پدی
    -0.67
    исленность
    -0.60
    Rüyada
    -0.59
    Jeografia
    -0.59
     CURIAM
    -0.58
    MigrationBuilder
    -0.57
    нгред
    -0.57
    POSITIVE LOGITS
    !!
    0.43
    !!!
    0.41
    ?!
    0.40
    ?!?
    0.39
     folks
    0.38
     !!!
    0.38
    UnusedPrivate
    0.37
    !?!
    0.37
     !!
    0.36
     &
    0.36
    Activations Density 1.496%

    No Known Activations