© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 11754
    Prev
    Next
    INDEX
    Explanations

    references to specific model types or components in miniature or tabletop gaming

    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
     الحره
    -0.55
    Források
    -0.52
    lső
    -0.50
    clusion
    -0.49
    leiding
    -0.48
    quiry
    -0.46
    viewWillAppear
    -0.46
    gæ
    -0.44
    HEAST
    -0.43
    mű
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.76
     ProtoMessage
    0.73
    FieldBuilder
    0.72
    WebElementEntity
    0.69
     AssemblyProduct
    0.66
     useCallback
    0.60
    serviceWorker
    0.60
     ComVisible
    0.60
    migrationBuilder
    0.58
     виправивши
    0.57
    Activations Density 0.076%

    No Known Activations