© 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. 22-GEMMASCOPE-RES-16K
    11. 10775
    Prev
    Next
    INDEX
    Explanations

    technical terms and code structures related to programming functions and libraries

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

    Tokens followed by positioning words (above, below)

    np_acts-logits-general · gemini-2.0-flash

    node above other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FROM
    -0.79
    WHEN
    -0.70
    WITH
    -0.69
    HERE
    -0.68
    AFTER
    -0.68
    BEFORE
    -0.64
    WITHOUT
    -0.63
    MigrationBuilder
    -0.60
    WHERE
    -0.60
    ABOUT
    -0.59
    POSITIVE LOGITS
    __(/*!
    0.77
     تضيفلها
    0.75
     Вікіпе
    0.69
    RetentionPolicy
    0.66
     članak
    0.65
    forChild
    0.65
    basicConfig
    0.64
    SuccessListener
    0.64
    Revenir
    0.64
    angerie
    0.62
    Activations Density 0.666%

    No Known Activations