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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 124008
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to prevalence and dominance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rungsseite
    -0.64
    Datuak
    -0.52
    Życiorys
    -0.52
     protoimpl
    -0.49
    sidemargin
    -0.49
    labelledby
    -0.47
    তথ্যসূত্র
    -0.46
    asteroido
    -0.46
    providedIn
    -0.46
     fashiola
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.52
    setVerticalGroup
    0.47
    Personensuche
    0.46
    ItemBackground
    0.44
     Öffentlichkeit
    0.36
     contextLoads
    0.35
     فريبيس
    0.35
     урна
    0.35
    󠁴
    0.34
    новништво
    0.33
    Activations Density 0.078%

    No Known Activations