© 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. 9578
    Prev
    Next
    INDEX
    Explanations

    specialized syntax or patterns in programming or data structures

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

    string literals and quoted text values in code and data structures.

    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
    RectangleBorder
    -0.80
    ніципалі
    -0.77
    Xna
    -0.73
     propOrder
    -0.71
    ſelf
    -0.69
    ſelves
    -0.69
    astéroïdes
    -0.68
    ьаж
    -0.66
     كومونز
    -0.66
    itinéraire
    -0.66
    POSITIVE LOGITS
    0
    0.46
     yes
    0.43
    null
    0.42
    string
    0.42
    yes
    0.41
    <td>
    0.40
    false
    0.40
    https
    0.40
     Öffentlichkeit
    0.39
    none
    0.39
    Activations Density 1.525%

    No Known Activations