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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15713
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting symbols used in programming or markup languages

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

    Text separated by vertical bars

    np_acts-logits-general · gemini-2.0-flash

    pipes and separators

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    ChildScrollView
    -0.70
    AddTagHelper
    -0.68
    WebElementEntity
    -0.59
    expandindo
    -0.56
    openConnection
    -0.54
    RectangleBorder
    -0.54
    makeText
    -0.52
    ReusableCell
    -0.51
    HomeAsUpEnabled
    -0.50
    ngrx
    -0.49
    POSITIVE LOGITS
     |
    0.59
    +|
    0.58
    |
    0.53
    .|
    0.52
    _|
    0.52
    -|
    0.52
     $|
    0.52
    ]|
    0.50
    }|
    0.48
    "|
    0.48
    Activations Density 0.174%

    No Known Activations