© 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. 11341
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data types in code

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

    Strings and string-related terms

    np_acts-logits-general · gemini-2.0-flash

    string type declarations

    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
    PhysRev
    -0.51
    NUM
    -0.46
    Див
    -0.46
     an
    -0.45
     numer
    -0.45
     true
    -0.45
    nextInt
    -0.44
    nums
    -0.44
    Numbers
    -0.44
    Numer
    -0.43
    POSITIVE LOGITS
     String
    2.02
    String
    1.97
     string
    1.74
    string
    1.65
    NSString
    1.51
     STRING
    1.46
     strings
    1.46
     Strings
    1.44
    STRING
    1.42
    字符串
    1.40
    Activations Density 0.174%

    No Known Activations