© 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. 3-GEMMASCOPE-RES-16K
    11. 1780
    Prev
    Next
    INDEX
    Explanations

    quantitative variables and parameters related to physical and mathematical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     free
    -0.49
     fully
    -0.43
    greenrobot
    -0.43
     end
    -0.43
     in
    -0.42
     transfert
    -0.42
     ar
    -0.41
    assertNotNull
    -0.41
    atam
    -0.41
     ha
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.79
    .*")]
    0.75
    енча
    0.74
    LookAnd
    0.73
     مشين
    0.72
     GIPHY
    0.71
     Mahomet
    0.70
    tvguidetime
    0.69
    ]--;
    0.68
     FetchType
    0.68
    Activations Density 1.008%

    No Known Activations