Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 123289
    Prev
    Next
    INDEX
    Explanations

    references to family planning and related conversations or methods

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

    personal names and specific locations

    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
    rungsseite
    -0.69
    ViewFeatures
    -0.51
    Espèce
    -0.46
     liggen
    -0.45
     dezelve
    -0.45
     rústica
    -0.44
     decoración
    -0.43
    intendent
    -0.42
    Искәрмәләр
    -0.42
    MERCIAL
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.60
    strijden
    0.41
    WillAppear
    0.41
     brilh
    0.38
    multer
    0.38
     encouragement
    0.36
     crossorigin
    0.36
     iprot
    0.36
    AVR
    0.35
     intervention
    0.35
    Activations Density 0.020%

    No Known Activations