© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6726
    Prev
    Next
    INDEX
    Explanations

    patterns related to data validation and numerical checks

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

    technical programming and validation-related terms, especially around input validation, regular expressions, and data type checking.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.41
    tagHelperRunner
    -0.35
    ритори
    -0.33
    开门
    -0.32
     thăm
    -0.31
     continental
    -0.31
     umbi
    -0.31
    provision
    -0.30
     reunite
    -0.30
     прока
    -0.30
    POSITIVE LOGITS
    WireFormatLite
    0.75
    PerformLayout
    0.60
    ftagPool
    0.53
    Personendaten
    0.53
    Atoi
    0.52
    QMetaType
    0.50
    MethodManager
    0.49
    parsedMessage
    0.49
    śmie
    0.48
    IndentedString
    0.48
    Activations Density 0.132%

    No Known Activations