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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53388
    Prev
    Next
    INDEX
    Explanations

    mentions of "high school."

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

    High School

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.77
    addCriterion
    -0.74
    Geplaatst
    -0.70
    ագրություններ
    -0.70
     يتيمه
    -0.66
    AndEndTag
    -0.66
    MigrationBuilder
    -0.65
    İstinadlar
    -0.65
    はじめに
    -0.65
     Nebel
    -0.64
    POSITIVE LOGITS
     School
    0.54
    Slf
    0.52
     commiss
    0.48
    infan
    0.47
    fame
    0.46
    imetsu
    0.45
    FirebaseDatabase
    0.44
    stdafx
    0.44
    idopsis
    0.43
    Soc
    0.42
    Activations Density 0.021%

    No Known Activations