© 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. 11-GEMMASCOPE-RES-16K
    11. 8421
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or specific formatting notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.67
     Chun
    -0.65
    ̍
    -0.61
    Chun
    -0.60
     kaynağından
    -0.58
     entre
    -0.56
     The
    -0.55
    apuram
    -0.55
     *__
    -0.53
    enk
    -0.53
    POSITIVE LOGITS
    Datuak
    1.30
     greateſt
    1.08
    +#+
    1.04
     ſtate
    1.02
     Reſ
    0.99
     pleaſure
    0.98
     Offisielt
    0.94
     houſe
    0.93
     Jefus
    0.91
     beſt
    0.91
    Activations Density 0.441%

    No Known Activations