© 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. 22-GEMMASCOPE-RES-16K
    6. 10148
    Prev
    Next
    INDEX
    Explanations

    identifiers and keywords in code snippets related to data structure definitions and operations

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

    Followed by "set"

    np_acts-logits-general · gemini-2.0-flash

    programming 'set' keyword

    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
     NSCoder
    -0.93
    ReusableCell
    -0.81
     مشين
    -0.76
    TemporalType
    -0.73
    GEBURTSDATUM
    -0.73
     виправивши
    -0.73
    Personensuche
    -0.68
    MigrationBuilder
    -0.67
     /\.(
    -0.66
    EndGlobalSection
    -0.65
    POSITIVE LOGITS
     set
    3.74
     Set
    3.33
    set
    3.16
    Set
    3.09
     sets
    2.87
     SET
    2.86
     setting
    2.71
    SET
    2.58
     Sets
    2.58
     Setting
    2.43
    Activations Density 0.532%

    No Known Activations