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. 34-GEMMASCOPE-RES-16K
    6. 11591
    Prev
    Next
    INDEX
    Explanations

    closing brackets and related syntax structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.82
    enablog
    -0.76
     للمعارف
    -0.75
    IVEREF
    -0.75
    AndEndTag
    -0.74
     tartalomajánló
    -0.71
    Tikang
    -0.71
    
    -0.69
    endphp
    -0.69
     estekak
    -0.69
    POSITIVE LOGITS
     //
    1.46
    //
    1.05
     /*
    0.95
    ;//
    0.86
     ///
    0.84
    ,//
    0.81
     —
    0.81
     {//
    0.81
    ();//
    0.78
    /*
    0.76
    Activations Density 1.663%

    No Known Activations