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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 95172
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "name" and its variations in different contexts

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

    name as a key

    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
     JSTOR
    -0.57
     Cec
    -0.57
    ⅘
    -0.54
     Dij
    -0.54
    FTFY
    -0.54
     Rochester
    -0.54
    soph
    -0.53
     Chill
    -0.52
     Pollo
    -0.51
    stiff
    -0.51
    POSITIVE LOGITS
    Name
    1.29
     name
    1.28
    name
    1.20
     Name
    1.20
    NAME
    1.16
     NAME
    1.12
    setName
    0.99
     names
    0.96
     setName
    0.91
     Names
    0.90
    Activations Density 0.061%

    No Known Activations