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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62259
    Prev
    Next
    INDEX
    Explanations

    mentions of personal experiences or anecdotes in a conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ᅠ
    -0.54
    цездатний
    -0.50
     AssemblyCulture
    -0.48
    mybatisplus
    -0.45
    stdc
    -0.44
    tiefel
    -0.44
    CppMethod
    -0.43
    setVerticalGroup
    -0.43
     useAppContext
    -0.42
    sukienka
    -0.41
    POSITIVE LOGITS
     Paglinawan
    0.43
    SourceChecksum
    0.41
    AndEndTag
    0.40
     wako
    0.40
    nesc
    0.36
    Wrapped
    0.36
     espir
    0.35
     Reel
    0.35
     pageContext
    0.35
    Personensuche
    0.35
    Activations Density 0.012%

    No Known Activations