© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3636
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure related to functions and code execution

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

    whitespace and indentation tokens in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zwiſchen
    -1.29
     queſta
    -1.23
    <unused28>
    -1.22
    <unused17>
    -1.22
    <unused43>
    -1.22
    <unused41>
    -1.22
    [@BOS@]
    -1.22
    <unused8>
    -1.21
    <unused3>
    -1.21
    <pad>
    -1.21
    POSITIVE LOGITS
     
    0.35
      
    0.35
    <strong>
    0.31
    '
    0.30
    The
    0.28
    ↵↵
    0.26
    ↵
    0.26
    T
    0.26
    S
    0.25
    <b>
    0.25
    Activations Density 1.849%

    No Known Activations