© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10640
    Prev
    Next
    INDEX
    Explanations

    keywords related to matching algorithms and operations

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

    Tokens followed by "match" or "matches"

    np_acts-logits-general · gemini-2.0-flash

    finding matches

    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
     CreateTagHelper
    -0.87
     kasarigan
    -0.80
    endphp
    -0.65
     '\\;'
    -0.62
    thâu
    -0.59
     שוליים
    -0.56
    AndEndTag
    -0.55
    HtmlAttribute
    -0.54
    Билгалдахарш
    -0.54
    StoreMessageInfo
    -0.53
    POSITIVE LOGITS
     match
    4.06
    match
    3.72
     Match
    3.63
     matching
    3.62
    Match
    3.52
     MATCH
    3.35
     matched
    3.32
     Matching
    3.30
     matches
    3.24
    matching
    3.14
    Activations Density 0.320%

    No Known Activations