Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 2091
    Prev
    Next
    INDEX
    Explanations

    terms related to matching or compatibility in various contexts

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

    The token "match"

    np_acts-logits-general · gemini-2.0-flash

    match and its variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    μφωνα
    -0.58
    Przypisy
    -0.57
     referenties
    -0.57
    hehehe
    -0.57
     généraux
    -0.57
    hehe
    -0.56
     ferma
    -0.55
    onucleotide
    -0.53
    /−
    -0.53
    ए
    -0.52
    POSITIVE LOGITS
     MATCH
    1.06
     Match
    1.00
     Matches
    0.97
    MATCH
    0.97
     matches
    0.94
    matches
    0.85
     match
    0.85
    Match
    0.83
     wits
    0.81
    match
    0.80
    Activations Density 0.082%

    No Known Activations