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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 51328
    Prev
    Next
    INDEX
    Explanations

    high-activation error handling and debugging-related expressions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming code and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.55
    endphp
    -0.53
    CppMethod
    -0.53
    oredCriteria
    -0.50
     Dernière
    -0.48
    ThroughAttribute
    -0.47
    })->
    -0.47
     autorytatywna
    -0.46
    انيف
    -0.44
    {}",
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.40
     whereby
    0.39
    (()=>{
    0.39
     aéri
    0.38
    awaiter
    0.37
    setcounter
    0.36
    itself
    0.36
    Біографія
    0.36
    himself
    0.36
     alfombra
    0.35
    Activations Density 0.003%

    No Known Activations