© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    indicators of numerical values or calculations

    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
    }{*}{
    -0.66
     Schuyler
    -0.62
     Grady
    -0.58
     Pearson
    -0.58
     Quinn
    -0.58
     Ch
    -0.57
    setResult
    -0.56
    שרה
    -0.55
     Ha
    -0.54
     McClure
    -0.53
    POSITIVE LOGITS
     Reſ
    0.93
     ſta
    0.91
     Efq
    0.91
     Diſ
    0.90
    ReusableCell
    0.88
     Inſ
    0.86
    ſelves
    0.86
     Theſe
    0.82
     Conſ
    0.82
     Jefus
    0.82
    Activations Density 0.245%

    No Known Activations