© 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. 20-GEMMASCOPE-RES-16K
    11. 14605
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements, particularly related to structure and initialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens (e.g., parent, MODULE, class)

    np_acts-logits-general · gemini-2.0-flash

    prefixed with "__"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.50
     R
    -0.43
    oti
    -0.42
    ob
    -0.41
    ad
    -0.40
    3
    -0.40
    dado
    -0.40
    ǎ
    -0.40
    ale
    -0.39
     הר
    -0.39
    POSITIVE LOGITS
    __
    1.66
     __
    1.59
    .__
    1.36
    &__
    1.31
    (!__
    1.22
    )__
    1.20
    __'
    1.20
    ::__
    1.18
    ->__
    1.17
    (__
    1.15
    Activations Density 0.083%

    No Known Activations