© 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. 3080
    Prev
    Next
    INDEX
    Explanations

    numeric representations and programming structures

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

    Characters followed by a number

    np_acts-logits-general · gemini-2.0-flash

    expressions with variables

    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
    EndGlobalSection
    -0.68
     propOrder
    -0.63
    queryInterface
    -0.61
    TypedDataSet
    -0.59
    StoryboardSegue
    -0.58
    UserScript
    -0.58
     resourceCulture
    -0.57
    ArgumentParser
    -0.56
    DropTable
    -0.55
     ویکی‌پدیای
    -0.55
    POSITIVE LOGITS
    b
    1.05
    c
    1.04
    y
    1.02
    t
    1.00
    g
    0.99
    f
    0.98
    d
    0.97
    p
    0.97
    h
    0.95
    m
    0.94
    Activations Density 1.920%

    No Known Activations