© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3607
    Prev
    Next
    INDEX
    Explanations

    elements of programming code and structure

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

    parsing and deserialization of structured data objects from various formats (JSON, database cursors, XML).

    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
     виправивши
    -0.62
    endphp
    -0.60
     estekak
    -0.58
     $_(
    -0.58
     HasFactory
    -0.57
     utafitiHapana
    -0.55
     cetera
    -0.54
    tldr
    -0.53
     resourceCulture
    -0.53
    Rhestr
    -0.53
    POSITIVE LOGITS
    ——
    0.57
    －
    0.56
    Ⅰ
    0.56
     juge
    0.55
    ：
    0.55
    isShow
    0.55
    ￥
    0.53
    ；
    0.52
    ，
    0.51
     jugement
    0.50
    Activations Density 0.610%

    No Known Activations