© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    numerical values and structured lists

    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
    fromCharCode
    -0.59
    Portale
    -0.56
    Portail
    -0.52
    kirch
    -0.50
    顺
    -0.50
    ctable
    -0.50
    Looper
    -0.48
    richTextPanel
    -0.48
    rawDesc
    -0.47
    ríguez
    -0.46
    POSITIVE LOGITS
     StatefulWidget
    0.81
     StatelessWidget
    0.72
     lenker
    0.70
    providedIn
    0.62
     lú
    0.57
     InputDecoration
    0.56
    ValueStyle
    0.55
    BASEPATH
    0.54
    AutoScaleMode
    0.54
    Exterior
    0.53
    Activations Density 0.979%

    No Known Activations