© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11480
    Prev
    Next
    INDEX
    Explanations

    statements related to major outcomes or impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hurtig
    -0.44
    fören
    -0.44
    致
    -0.43
    ByExample
    -0.42
     juridiques
    -0.42
     regelmatig
    -0.42
     fören
    -0.41
     varje
    -0.41
     kecamatan
    -0.41
     recevez
    -0.41
    POSITIVE LOGITS
    MENAFN
    0.72
     تضيفلها
    0.70
    DoubleQuotes
    0.69
    IsContent
    0.69
    writeFieldEnd
    0.68
    UnusedPrivate
    0.66
    thenReturn
    0.65
    enderror
    0.65
    volve
    0.60
    íncia
    0.59
    Activations Density 0.787%

    No Known Activations