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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70709
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of text blocks or sections

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

    A special token "bos" appearing within triple brackets that marks the beginning of a text sequence or document in a corpus.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     intptr
    -0.55
    ValueStyle
    -0.51
    #+#
    -0.51
     समीक्षाओं
    -0.51
    IUrlHelper
    -0.49
    webElement
    -0.48
    XmlAccessType
    -0.47
     Administrativna
    -0.47
    XmlAccessorType
    -0.45
    LookAnd
    -0.45
    POSITIVE LOGITS
    '&:
    0.41
     gâteau
    0.39
     духовке
    0.38
    AddTagHelper
    0.38
     cuantas
    0.37
     ProtoMessage
    0.36
     secciones
    0.35
    ollectionView
    0.35
    splitlines
    0.35
    Cordialement
    0.35
    Activations Density 0.089%

    No Known Activations