© 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. 10045
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax used in programming languages, specifically focusing on class definitions and field specifications

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

    SQL, data type, or programming code

    np_acts-logits-general · gemini-2.0-flash

    programming data types

    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
    ponses
    -0.68
    Rhestr
    -0.62
    Condol
    -0.59
     AssemblyCompany
    -0.55
     "..\..\
    -0.55
    HandlerContext
    -0.53
    ForResult
    -0.52
     @[
    -0.52
    ISupport
    -0.51
    ElementException
    -0.50
    POSITIVE LOGITS
    awtextra
    0.72
    AccessorTable
    0.70
    ]-->
    0.60
     insuffisamment
    0.59
    mybatisplus
    0.59
    timestamps
    0.57
    boolean
    0.53
     integer
    0.53
    .*")]
    0.53
    parsedMessage
    0.52
    Activations Density 0.058%

    No Known Activations