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. 40735
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or structures in data

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

    patients and women

    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
    <?
    -0.52
     indígen
    -0.51
     óptica
    -0.50
     Kebijakan
    -0.47
     directiva
    -0.46
     serpiente
    -0.44
     căr
    -0.43
     préstamos
    -0.43
     burbuja
    -0.43
    cartão
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.63
     Numerade
    0.59
     autorytatywna
    0.56
    tagHelperRunner
    0.56
     Roskov
    0.53
     незавершена
    0.53
    Попис
    0.53
    Diweddarwch
    0.52
    XmlAccessType
    0.47
    хьтан
    0.47
    Activations Density 0.001%

    No Known Activations