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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 98158
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at."

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

    word endings like "at" or "ats"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.57
    ParallelGroup
    -0.55
    ंदीखरीदारी
    -0.54
    cstring
    -0.53
    ConverterFactory
    -0.52
    الحياه
    -0.52
    ercito
    -0.52
     otomatig
    -0.51
     Vikipedi
    -0.51
    símbolo
    -0.50
    POSITIVE LOGITS
    at
    2.19
    AT
    1.57
    ats
    1.05
    At
    1.03
     At
    0.94
    atat
    0.91
     AT
    0.87
    yat
    0.85
    atly
    0.82
    mat
    0.82
    Activations Density 0.034%

    No Known Activations