© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1211
    Prev
    Next
    INDEX
    Explanations

    tokens that represent structuring elements or indicators in programming, specifically for code block initiation or server interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ujednoznacz
    -0.72
     utafitiHapana
    -0.70
    ----</
    -0.67
    %</
    -0.64
    processable
    -0.59
    ніципа
    -0.57
     Efq
    -0.57
    tisseur
    -0.56
    tvguidetime
    -0.56
    ControllerAdvice
    -0.55
    POSITIVE LOGITS
    AnchorStyles
    0.76
    WebVitals
    0.60
     initComponents
    0.60
    awtextra
    0.60
    richTextPanel
    0.59
    TagMode
    0.56
     دى
    0.55
    principalColumn
    0.54
    findpost
    0.53
     печени
    0.53
    Activations Density 0.022%

    No Known Activations