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. 24464
    Prev
    Next
    INDEX
    Explanations

    references to stories and narrative elements

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

    stories and funny content

    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
    protoimpl
    -0.36
    ffl
    -0.35
    jsonwebtoken
    -0.34
    Measured
    -0.33
    Ligações
    -0.33
    <?
    -0.32
    gathered
    -0.32
    verifyException
    -0.31
    heter
    -0.31
    Notae
    -0.31
    POSITIVE LOGITS
    hoeddwyd
    0.58
     Italijanski
    0.56
    tagHelperRunner
    0.56
    MLLoader
    0.54
    WebServlet
    0.53
    المشاركات
    0.48
     Numerade
    0.47
    UrlResolution
    0.46
    expandindo
    0.46
    EndGlobalSection
    0.46
    Activations Density 0.233%

    No Known Activations