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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14918
    Prev
    Next
    INDEX
    Explanations

    various character types and their usage in passwords and regular expressions

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

    character class patterns and specifications in regular expressions and code syntax.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     term
    -0.40
    DockStyle
    -0.38
     IFTT
    -0.37
     critical
    -0.36
    bitField
    -0.35
    internalType
    -0.35
    FieldBuilder
    -0.35
     élastique
    -0.35
     NSCoder
    -0.34
     plead
    -0.33
    POSITIVE LOGITS
     numerals
    1.01
     numbers
    0.98
     Numbers
    0.94
     digits
    0.93
     Numer
    0.90
    isdigit
    0.89
     chiffres
    0.88
    Numbers
    0.88
     NUMBERS
    0.87
    numbers
    0.86
    Activations Density 0.370%

    No Known Activations