© 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. 6535
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and stipulations regarding responsibilities and limitations of liability

    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
    ThroughAttribute
    -0.57
    einander
    -0.57
    можно
    -0.55
    inafter
    -0.55
    MessageOf
    -0.55
    RenderAtEndOf
    -0.50
    entiary
    -0.49
    })]
    -0.49
    wreck
    -0.48
    ptid
    -0.48
    POSITIVE LOGITS
     directly
    0.56
    pompa
    0.54
     diret
    0.54
    (!__
    0.54
    Билгалдахарш
    0.53
    دانشنامهٔ
    0.53
    <bos>
    0.53
     виправивши
    0.53
    directly
    0.53
     Directly
    0.50
    Activations Density 0.640%

    No Known Activations