© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8311
    Prev
    Next
    INDEX
    Explanations

    occurrences of the data type "double" and its related attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.97
     للاسماء
    -0.87
    IsContent
    -0.84
    .*")]
    -0.83
    Santis
    -0.76
     oreille
    -0.76
     newBuilder
    -0.74
    getFont
    -0.74
    WireFormatLite
    -0.74
    Datuak
    -0.73
    POSITIVE LOGITS
    double
    2.03
     double
    2.01
    Double
    1.91
     DOUBLE
    1.91
     Double
    1.91
    DOUBLE
    1.85
     doubles
    1.76
    doubles
    1.68
     Doubles
    1.64
    Doubles
    1.59
    Activations Density 0.040%

    No Known Activations