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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15149
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to matching and comparison

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

    "match" or "matching"

    np_acts-logits-general · gemini-2.0-flash

    match / matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     newUser
    -0.69
    Portale
    -0.63
    errHandler
    -0.59
    newUser
    -0.51
    execSQL
    -0.50
    anthene
    -0.49
     newName
    -0.47
    ८
    -0.46
     isFirst
    -0.46
     esternos
    -0.45
    POSITIVE LOGITS
     match
    1.31
     Match
    1.30
    match
    1.27
    Match
    1.23
     MATCH
    1.21
    MATCH
    1.12
     matches
    0.98
     matched
    0.97
    matched
    0.94
     Matches
    0.94
    Activations Density 0.094%

    No Known Activations