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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 61865
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of the word "name" and its derivatives in various contexts

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

    people's names

    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
     Royaume
    -0.37
     policiers
    -0.35
    bundles
    -0.35
     durumda
    -0.34
     duração
    -0.34
    Préparation
    -0.34
    sessions
    -0.34
    retudo
    -0.33
    失礼
    -0.33
    vres
    -0.33
    POSITIVE LOGITS
     name
    1.20
     names
    1.09
     NAME
    0.94
     NAMES
    0.90
    名字
    0.89
     Names
    0.88
    name
    0.88
     Name
    0.87
    Name
    0.84
    NAME
    0.83
    Activations Density 0.021%

    No Known Activations