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. 3390
    Prev
    Next
    INDEX
    Explanations

    structured data and identifiers related to programming and database operations

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

    Strings associated with names or identifiers

    np_acts-logits-general · gemini-2.0-flash

    string identifiers

    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
    KindOfClass
    -0.63
    memset
    -0.62
    >");
    
    -0.61
    ={
    
    -0.58
    >`;
    -0.57
    aged
    -0.56
    )");
    
    -0.56
     isinstance
    -0.56
    UserDTO
    -0.56
    UnitPrice
    -0.56
    POSITIVE LOGITS
    DoubleQuotes
    0.75
     string
    0.74
     String
    0.64
    String
    0.61
    writeFieldEnd
    0.59
    ChromeDriver
    0.57
    Str
    0.56
    OrNil
    0.54
     STRING
    0.53
    IBarButtonItem
    0.52
    Activations Density 0.314%

    No Known Activations