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. 35-GEMMASCOPE-RES-16K
    6. 12431
    Prev
    Next
    INDEX
    Explanations

    programming and dialog-related elements in software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.38
    الحياه
    -0.35
    انگلیسی
    -0.31
     herrs
    -0.31
    SequentialGroup
    -0.30
    wezen
    -0.30
    URLEncoder
    -0.29
    bihan
    -0.29
    bindParam
    -0.28
    adə
    -0.28
    POSITIVE LOGITS
     dialog
    1.91
     Dialog
    1.72
    dialog
    1.63
     dialogue
    1.62
     popup
    1.59
     pop
    1.58
     dialogues
    1.55
     DIALOG
    1.55
    Dialog
    1.52
     Dialogue
    1.38
    Activations Density 0.437%

    No Known Activations