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. 64708
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and periods at the end of sentences

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

    names with initials

    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
     autorytatywna
    -0.68
    GEBURTSDATUM
    -0.67
    uxxxx
    -0.67
    webElementXpaths
    -0.65
    fromnode
    -0.64
     ویکی‌پدی
    -0.63
     Infórmanos
    -0.63
    +#+#
    -0.60
    tangentMode
    -0.60
    帖最后由
    -0.60
    POSITIVE LOGITS
    PLIED
    0.35
    IBILITIES
    0.33
     sessionId
    0.33
    つまみ
    0.32
    无双
    0.32
    amatan
    0.32
     Guitars
    0.31
    thyst
    0.30
     Productions
    0.30
    Nicholas
    0.30
    Activations Density 0.025%

    No Known Activations