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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 64853
    Prev
    Next
    INDEX
    Explanations

    concepts related to autonomy and independence in work or research contexts

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

    user registration and questionnaires

    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
    ChildScrollView
    -0.47
     jouet
    -0.40
     étoit
    -0.39
    zzleHttp
    -0.37
    MouseAdapter
    -0.35
     disambiguazione
    -0.35
    arakhand
    -0.34
    queryInterface
    -0.34
     enfance
    -0.34
     tez
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.49
     autonomia
    0.48
    évaluateur
    0.48
     nonUne
    0.47
     unsupervised
    0.46
     препратки
    0.46
     autonomy
    0.44
     sarili
    0.44
     tự
    0.44
    ConstraintMaker
    0.44
    Activations Density 0.052%

    No Known Activations