© 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. 15919
    Prev
    Next
    INDEX
    Explanations

    names of individuals and institutions associated with legal and academic contexts

    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
     Solano
    -0.94
     Xander
    -0.92
     Marcell
    -0.92
     Yud
    -0.86
     Kea
    -0.83
     Bhutan
    -0.82
     Ricard
    -0.82
     SFR
    -0.80
     Guinea
    -0.80
     GX
    -0.79
    POSITIVE LOGITS
     Shaw
    0.90
    Shaw
    0.82
    UTERS
    0.79
     Bajaj
    0.76
     SIMBAD
    0.72
     Alonso
    0.71
     SHAW
    0.70
     Dwyer
    0.68
     bose
    0.68
     Kaw
    0.67
    Activations Density 1.787%

    No Known Activations