© 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. 8915
    Prev
    Next
    INDEX
    Explanations

    coding syntax and programming constructs

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

    Code syntax or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    get/get/is/set methods

    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
     Sch
    -0.48
    كة
    -0.46
    OrderInfo
    -0.42
     surgir
    -0.42
    stø
    -0.41
    OrderStatus
    -0.41
    OrderID
    -0.41
     raras
    -0.41
    的
    -0.41
     G
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    1.27
    Personensuche
    1.12
    parsedMessage
    1.09
    writeFieldEnd
    1.08
    LookAnd
    1.07
    RenderAtEndOf
    1.04
     ujednoznacz
    1.03
    IUrlHelper
    1.02
     purpoſe
    1.01
     ſever
    1.00
    Activations Density 0.281%

    No Known Activations