© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 6947
    Prev
    Next
    INDEX
    Explanations

    file paths or directory structures within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    года
    -0.52
     Serializable
    -0.52
    ابقة
    -0.49
     Schoen
    -0.49
     evidently
    -0.49
     Boek
    -0.49
     Scherer
    -0.48
    سرائيل
    -0.48
    getFull
    -0.47
     Forma
    -0.47
    POSITIVE LOGITS
    PreferredItem
    1.25
    CloseOperation
    1.07
    webElementXpaths
    1.02
     المعيارى
    0.99
    migrationBuilder
    0.97
     ProtoMessage
    0.91
     مشين
    0.90
    MigrationBuilder
    0.89
     nahilalakip
    0.89
    PropertyChanging
    0.88
    Activations Density 0.038%

    No Known Activations