© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 1316
    Prev
    Next
    INDEX
    Explanations

    elements related to generic programming and the structure of class and method definitions in Java

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

    `Long`, `int`, `entity`, `user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     pool
    -0.40
     bar
    -0.38
    ma
    -0.35
     kap
    -0.35
     seed
    -0.33
     Pool
    -0.33
     tag
    -0.33
     sk
    -0.33
     auto
    -0.33
     j
    -0.33
    POSITIVE LOGITS
     defaultstate
    0.96
     <<<<<<<<<<<<<<
    0.91
     AssemblyTitle
    0.84
    tvguidetime
    0.71
     initComponents
    0.66
     NSCoder
    0.66
     ब्रेकडाउन
    0.66
     Signalez
    0.63
    LookAnd
    0.62
    ReusableCell
    0.61
    Activations Density 0.041%

    No Known Activations