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. 3-GEMMASCOPE-RES-16K
    6. 7752
    Prev
    Next
    INDEX
    Explanations

    occurrences of regular expression patterns and functions related to matching in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.75
    LookAnd
    -0.65
    Autoritní
    -0.64
     OFDb
    -0.62
     Audiodateien
    -0.62
    Datuak
    -0.58
     BorderRadius
    -0.58
     employes
    -0.58
     LNB
    -0.56
    marvin
    -0.56
    POSITIVE LOGITS
    match
    1.57
    Match
    1.46
     Match
    1.31
    MATCH
    1.26
     match
    1.15
    matches
    1.04
     MATCH
    1.01
    Matches
    1.00
     Matches
    0.94
     matches
    0.86
    Activations Density 0.128%

    No Known Activations