© 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. 3204
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical expressions and operations

    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
    Lähteet
    -0.50
     préfé
    -0.48
     épais
    -0.47
     privilégi
    -0.47
    bara
    -0.45
    }');
    -0.44
    établir
    -0.43
    uluş
    -0.43
    aro
    -0.43
     með
    -0.42
    POSITIVE LOGITS
    WithIOException
    0.70
    AnimationsModule
    0.69
    enumii
    0.69
    ConverterFactory
    0.69
     oprot
    0.68
    RenderAtEndOf
    0.68
    ">+
    0.66
    KommentareTeilen
    0.66
    
    0.66
    esModule
    0.64
    Activations Density 1.449%

    No Known Activations