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. 73507
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

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

    A period that marks the end of a sentence, often at the conclusion of a paragraph or section, sometimes followed by a line break.

    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
    +#+#
    -1.05
    RenderAtEndOf
    -0.83
     Roskov
    -0.74
    windowFixed
    -0.69
     المعيارى
    -0.69
     الرياضيه
    -0.65
     propOrder
    -0.62
     Photocase
    -0.60
    setVerticalGroup
    -0.60
    PreInfinity
    -0.59
    POSITIVE LOGITS
     both
    0.34
    धन
    0.33
    Ambos
    0.33
     ambos
    0.32
     båda
    0.32
    バーグ
    0.31
    Meanwhile
    0.31
     Oku
    0.31
     đựng
    0.29
     meanwhile
    0.29
    Activations Density 0.056%

    No Known Activations