© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    calls to action inviting participation or membership

    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
    chera
    -0.63
    erokee
    -0.60
    ichel
    -0.58
     Futura
    -0.58
     Neve
    -0.55
     noten
    -0.54
     mCurrent
    -0.53
     écoulé
    -0.53
     SLR
    -0.53
     Rauch
    -0.52
    POSITIVE LOGITS
     join
    3.35
     joining
    3.16
     joins
    3.08
     joined
    3.06
     Joining
    3.03
     JOIN
    2.95
    Joining
    2.89
     Join
    2.85
    join
    2.83
    JOIN
    2.74
    Activations Density 0.043%

    No Known Activations