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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8109
    Prev
    Next
    INDEX
    Explanations

    References to judicial standards, reviews, and rulings in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.57
    SharedCtor
    -0.56
     resourceCulture
    -0.55
     Comprometido
    -0.51
     nahilalakip
    -0.50
     Autorizaciones
    -0.48
     Infór
    -0.48
     idéia
    -0.47
     Италијани
    -0.47
    verifyException
    -0.47
    POSITIVE LOGITS
    iii
    0.47
    IIII
    0.46
    III
    0.45
    BeginInit
    0.43
    ii
    0.41
    Vii
    0.40
    IV
    0.40
    aip
    0.39
    viii
    0.39
    IB
    0.39
    Activations Density 0.197%

    No Known Activations