© 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. 11331
    Prev
    Next
    INDEX
    Explanations

    numeric values and sequences

    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
    ⓧ
    -0.84
    存于互联网档案馆
    -0.78
    GraphicsUnit
    -0.72
    Hochspringen
    -0.71
    }{*}{}
    -0.69
    GEBURTSDATUM
    -0.67
    verwijspagina
    -0.67
    rmtree
    -0.67
    astify
    -0.65
    enumi
    -0.64
    POSITIVE LOGITS
     للاسماء
    0.63
    licherweise
    0.62
     Gatsby
    0.61
    2
    0.57
     privadas
    0.56
     privados
    0.56
     עש
    0.54
    1
    0.54
     Vaticano
    0.53
    pernicus
    0.53
    Activations Density 1.074%

    No Known Activations