© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13665
    Prev
    Next
    INDEX
    Explanations

    informative references to patents and studies related to medical processes or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -1.00
    RenderAtEndOf
    -0.94
    RectangleBorder
    -0.89
    Hentet
    -0.87
    BagConstraints
    -0.85
    EndInit
    -0.83
     typelib
    -0.82
     Мексичка
    -0.80
    jsonwebtoken
    -0.78
     HasFactory
    -0.78
    POSITIVE LOGITS
    </blockquote>
    0.45
    ']));
    0.45
     proposes
    0.44
     p
    0.44
    ]):
    0.43
     discusses
    0.43
     *);
    0.43
    ']):
    0.42
     suggests
    0.41
    \}
    0.41
    Activations Density 1.657%

    No Known Activations