© 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. 4-GEMMASCOPE-RES-16K
    11. 958
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical models and random processes

    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
     advance
    -0.50
     advanced
    -0.49
    dje
    -0.47
    を進
    -0.46
     Advance
    -0.46
    abara
    -0.45
    ویری
    -0.45
    !
    -0.44
    Advance
    -0.43
     Advanced
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.91
    Personensuche
    0.90
     outliers
    0.88
    AndEndTag
    0.84
    scriptcase
    0.82
    writeField
    0.82
     typelib
    0.80
     outlier
    0.80
    featureID
    0.79
     Meksiku
    0.78
    Activations Density 1.923%

    No Known Activations