© 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. 25-GEMMASCOPE-RES-16K
    6. 12695
    Prev
    Next
    INDEX
    Explanations

    signals and error codes related to system processes and operations

    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
    marle
    -0.60
     aanbod
    -0.45
     Benth
    -0.44
     experiences
    -0.43
    wede
    -0.43
     city
    -0.42
    lankton
    -0.42
     Gehalt
    -0.42
    4
    -0.42
    érêt
    -0.42
    POSITIVE LOGITS
    ↵↵
    0.79
    ↵↵↵
    0.69
    }(),
    0.69
    */;
    0.68
    ↵
    0.67
    enderror
    0.66
    出版年
    0.66
    //</
    0.66
    //-----
    0.65
    etc
    0.64
    Activations Density 0.282%

    No Known Activations