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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 47108
    Prev
    Next
    INDEX
    Explanations

    punctuations and formatting cues in the text

    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
     répertoire
    -0.44
     chi̍t
    -0.39
    RectangleBorder
    -0.38
     Dostupné
    -0.37
    issory
    -0.37
    новниш
    -0.35
    InstanceState
    -0.35
     Altos
    -0.34
    HandlerContext
    -0.34
     restTemplate
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.62
    ViewFeatures
    0.57
     يتيمه
    0.56
    NameInMap
    0.51
     fotografico
    0.46
    VersionUID
    0.45
    denza
    0.44
    帖最后由
    0.44
    躇
    0.44
    BeginContext
    0.43
    Activations Density 0.098%

    No Known Activations