© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8815
    Prev
    Next
    INDEX
    Explanations

    specific prepositions and conjunctions that link various elements in complex sentences

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

    following "as", "a", "in", "to", "from"

    np_acts-logits-general · gemini-2.0-flash

    via free, additional loci, a mixture

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    spreis
    -0.32
     onBind
    -0.31
    ofType
    -0.29
     rapports
    -0.29
     ministère
    -0.28
    FileVersion
    -0.27
    страницу
    -0.27
     serce
    -0.26
     wyda
    -0.25
     upor
    -0.25
    POSITIVE LOGITS
    :✨
    0.71
    脚注の使い方
    0.67
    UnknownFieldSet
    0.61
     CreateTagHelper
    0.60
    DoubleQuotes
    0.58
    ьажоргаш
    0.58
     صوتيه
    0.58
    BeginContext
    0.57
     <=",
    0.56
    ArrowToggle
    0.55
    Activations Density 0.523%

    No Known Activations