© 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. 13766
    Prev
    Next
    INDEX
    Explanations

    judgmental or opinionated statements about individuals and their identities

    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
     مرئيه
    -0.71
    Geplaatst
    -0.61
    Jeografia
    -0.59
    ].)
    -0.59
    */}
    -0.57
     Audiodateien
    -0.56
    ="@+
    -0.55
     חיצוניים
    -0.53
     ")";
    -0.53
    */)
    -0.53
    POSITIVE LOGITS
     NSCoder
    0.58
    Nhưng
    0.57
     inderdaad
    0.56
     klingt
    0.50
    域名
    0.50
     σου
    0.50
    houding
    0.49
     Expédié
    0.49
     думать
    0.49
     पास
    0.49
    Activations Density 0.147%

    No Known Activations