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

    Neuronpedia

    APICircuit 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. 1580
    Prev
    Next
    INDEX
    Explanations

    legal language pertaining to court cases and rulings

    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
    pinch
    -0.38
     Wikime
    -0.32
    SHELL
    -0.31
     pinch
    -0.31
     мо
    -0.30
    Asthma
    -0.30
    ANNA
    -0.30
    Antonio
    -0.29
     ıs
    -0.29
     ADB
    -0.29
    POSITIVE LOGITS
    ⓧ
    0.76
     ModelExpression
    0.72
     dabei
    0.70
    IsContent
    0.70
     hierbei
    0.69
     therein
    0.67
     daarbij
    0.67
    Personensuche
    0.64
     resourceCulture
    0.63
     wtedy
    0.63
    Activations Density 1.051%

    No Known Activations