© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 55065
    Prev
    Next
    INDEX
    Explanations

    words and phrases with the "ack" sound, particularly in names

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

    ck, ack, ick, flock, Mack

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Vitale
    -0.61
     Lindgren
    -0.59
     MTA
    -0.58
     Â
    -0.57
    tableFuture
    -0.56
    groupId
    -0.56
     SOA
    -0.56
    VOA
    -0.55
     Reli
    -0.55
     Mili
    -0.55
    POSITIVE LOGITS
    ck
    0.98
    eck
    0.83
    ack
    0.82
    cks
    0.75
    ambién
    0.69
    ick
    0.69
     Cár
    0.69
     ack
    0.68
     Nacionales
    0.66
    cking
    0.66
    Activations Density 0.040%

    No Known Activations