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. 34-GEMMASCOPE-RES-16K
    6. 11033
    Prev
    Next
    INDEX
    Explanations

    code related to data parsing and manipulation in programming contexts

    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
    PropertyChanging
    -0.79
    principalColumn
    -0.71
     дописавши
    -0.71
    Tikang
    -0.69
    <unused41>
    -0.69
    <unused16>
    -0.69
    <unused43>
    -0.69
    <unused51>
    -0.69
    <pad>
    -0.69
    <unused8>
    -0.69
    POSITIVE LOGITS
    ↵
    0.29
    compile
    0.28
    Televis
    0.27
     tepat
    0.27
     Ribbon
    0.26
    カンド
    0.26
     pelaksanaan
    0.26
     damskie
    0.26
    A
    0.25
     demasiado
    0.25
    Activations Density 0.223%

    No Known Activations