© 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. 6023
    Prev
    Next
    INDEX
    Explanations

    JavaScript console logging statements and error handling

    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
     bague
    -0.82
    +#+#
    -0.82
    AnchorStyles
    -0.72
    bieter
    -0.72
     pouvoirs
    -0.71
     auroit
    -0.70
     aéri
    -0.70
    InSection
    -0.69
     avoient
    -0.68
     variétés
    -0.68
    POSITIVE LOGITS
     console
    1.65
     consoles
    1.48
     Console
    1.46
    console
    1.35
    Console
    1.24
    CONSOLE
    1.13
    SOLE
    0.94
     consol
    0.92
     consola
    0.86
     SCE
    0.78
    Activations Density 0.044%

    No Known Activations