© 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. 10-GEMMASCOPE-RES-16K
    6. 13540
    Prev
    Next
    INDEX
    Explanations

    location names and street addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLES
    -0.46
    巢
    -0.46
     Shed
    -0.45
     volontaire
    -0.45
     skor
    -0.44
     region
    -0.43
     regions
    -0.43
     wohl
    -0.43
    Dung
    -0.43
     https
    -0.42
    POSITIVE LOGITS
     Avenue
    1.00
     streets
    0.96
     street
    0.92
    IntoConstraints
    0.92
     boulevard
    0.88
     avenue
    0.87
     Streets
    0.85
    endphp
    0.82
    Streets
    0.82
    streets
    0.81
    Activations Density 0.068%

    No Known Activations