© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    references to the need for additional resources or improvements

    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
    KommentareTeilen
    -0.47
     total
    -0.42
    end
    -0.40
    total
    -0.39
    Биография
    -0.39
    ônica
    -0.39
    icz
    -0.39
    roen
    -0.38
     end
    -0.38
    ipzig
    -0.38
    POSITIVE LOGITS
    Personensuche
    1.13
     còn
    0.98
    twimg
    0.92
     jeszcze
    0.91
    Ещё
    0.91
     vielä
    0.88
    NameInMap
    0.85
     ještě
    0.84
     noch
    0.83
     még
    0.82
    Activations Density 0.531%

    No Known Activations