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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 33-GEMMASCOPE-RES-16K
    6. 11374
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML structure and data representation

    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
    pec
    -0.51
    ientras
    -0.49
     Afri
    -0.48
    iffance
    -0.45
    IBLIO
    -0.45
    enerbah
    -0.45
    ribu
    -0.44
    ofila
    -0.43
     Collie
    -0.43
    ison
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.61
    UseVisualStyle
    0.52
    الحياه
    0.52
    interopRequire
    0.48
     sanitaires
    0.47
    InjectMocks
    0.46
     initComponents
    0.46
     lenker
    0.46
    Étymologie
    0.45
     compromis
    0.45
    Activations Density 1.111%

    No Known Activations