© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5078
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax specific to programming languages, particularly enums and fields

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

    Enum declarations, access, and related code

    np_acts-logits-general · gemini-2.0-flash

    enum values and 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
    expandindo
    -0.51
     née
    -0.48
     prête
    -0.43
    NullException
    -0.43
    arashtra
    -0.43
    rayage
    -0.42
    itosti
    -0.42
    coran
    -0.42
     digress
    -0.42
    DebuggerNonUser
    -0.41
    POSITIVE LOGITS
     enum
    1.37
    Enum
    1.31
    enum
    1.26
     Enum
    1.23
     enums
    1.09
    ENUM
    1.07
    EnumValue
    1.05
    Enumerated
    0.98
    enums
    0.94
    EnumType
    0.94
    Activations Density 0.567%

    No Known Activations