Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7734
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, specifically for data processing or testing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HP
    -0.86
    Milli
    -0.83
    Packard
    -0.83
     Milli
    -0.82
     Packard
    -0.80
    HP
    -0.73
     Archibald
    -0.69
     Mahesh
    -0.66
     Centi
    -0.66
     Ced
    -0.65
    POSITIVE LOGITS
    ctx
    1.20
     ctx
    1.18
    Ctx
    0.86
    RuleContext
    0.83
    ImageContext
    0.81
    CTX
    0.77
     createContext
    0.73
     Grimes
    0.73
     Ethan
    0.73
     Mathi
    0.72
    Activations Density 1.564%

    No Known Activations