Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10983
    Prev
    Next
    INDEX
    Explanations

    terms related to configuration settings in programming context

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

    Code-related tokens and symbols

    np_acts-logits-general · gemini-2.0-flash

    environment variables and code constructs

    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
     textStatus
    -0.55
    ifoli
    -0.49
     pungkasnya
    -0.48
    )();
    -0.47
    的吗
    -0.47
     MonoBehaviour
    -0.46
    pierw
    -0.46
    XCTAssertEqual
    -0.46
    Bronnen
    -0.46
    amoja
    -0.45
    POSITIVE LOGITS
    @
    0.73
    ValueStyle
    0.68
    unless
    0.65
    IContainer
    0.60
    +#+#
    0.59
     Numerade
    0.58
    TypedDataSet
    0.58
     @
    0.58
    raise
    0.57
    IUrlHelper
    0.57
    Activations Density 0.096%

    No Known Activations