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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13882
    Prev
    Next
    INDEX
    Explanations

    code related to user management and database interactions

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

    Code snippets ending in periods or colons

    np_acts-logits-general · gemini-2.0-flash

    code creation and database operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModelProperty
    -0.56
    AnimationsModule
    -0.52
    vieux
    -0.51
    UpInside
    -0.49
    UMI
    -0.48
    dossier
    -0.47
    Umb
    -0.46
     exposure
    -0.46
     Gage
    -0.46
    FilterChain
    -0.45
    POSITIVE LOGITS
     ویکی‌پدیا
    0.57
    afone
    0.56
     parseFrom
    0.52
     ModelExpression
    0.52
    richTextPanel
    0.51
     يتيمه
    0.51
    ✨:
    0.51
    rrggbb
    0.51
     насеље
    0.49
     khảo
    0.48
    Activations Density 0.091%

    No Known Activations