© 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. 7-GEMMASCOPE-RES-16K
    11. 14927
    Prev
    Next
    INDEX
    Explanations

    occurrences of structure declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.81
     Normdatei
    -0.79
    Referințe
    -0.78
     LGB
    -0.76
     Halley
    -0.74
     Ena
    -0.73
    ंदीखरीदारी
    -0.73
     Viceroy
    -0.71
     Trafalgar
    -0.70
     Enigma
    -0.69
    POSITIVE LOGITS
    struct
    1.71
     struct
    1.69
     structs
    1.21
    Struct
    1.16
     Struct
    1.15
    structs
    1.03
    STRUCT
    0.94
     STRUCT
    0.83
    structing
    0.75
    StructField
    0.74
    Activations Density 0.067%

    No Known Activations