© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6445
    Prev
    Next
    INDEX
    Explanations

    quantitative assessments and expressions of significance or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    скар
    -0.60
     decl
    -0.56
     rá
    -0.53
    br
    -0.51
     ок
    -0.49
     no
    -0.49
     form
    -0.49
     lep
    -0.48
    tific
    -0.48
     mno
    -0.48
    POSITIVE LOGITS
     cât
    0.78
     économies
    0.77
     câte
    0.73
     combien
    0.73
     jScrollPane
    0.73
    PYX
    0.71
     banques
    0.69
    expandindo
    0.67
    IntoConstraints
    0.66
    Executives
    0.66
    Activations Density 0.064%

    No Known Activations