Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 861
    Prev
    Next
    INDEX
    Explanations

    coding elements and syntax commonly used in programming and software development

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

    provide the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     baik
    -0.35
    JSONException
    -0.34
     su
    -0.34
    AddWithValue
    -0.33
    หมือน
    -0.33
     fast
    -0.32
    awaiter
    -0.32
     dafür
    -0.32
     considérons
    -0.31
     erw
    -0.31
    POSITIVE LOGITS
    expandindo
    0.69
    setVerticalGroup
    0.67
    <unused43>
    0.66
    <unused3>
    0.66
    <unused41>
    0.66
    <pad>
    0.66
    <unused28>
    0.66
    <unused74>
    0.66
    [@BOS@]
    0.65
    <unused8>
    0.65
    Activations Density 0.004%

    No Known Activations