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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 24550
    Prev
    Next
    INDEX
    Explanations

    conditional statements and qualifiers

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

    Characters or tokens that serve as separators or delimiters in text, particularly punctuation marks, line breaks, and spacing in structured documents like code or formatted text.

    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
    
    -0.65
    nloa
    -0.53
    ContentAsync
    -0.52
    原始内容存档
    -0.51
    KommentareTeilen
    -0.50
     مرئيه
    -0.49
    YMMV
    -0.48
    GEBURTS
    -0.48
    ruik
    -0.47
     dAtA
    -0.46
    POSITIVE LOGITS
    dyr
    0.40
    src
    0.40
    wikk
    0.38
     TREAT
    0.36
     eye
    0.35
    Sign
    0.35
     وث
    0.35
    olf
    0.35
     SIGN
    0.35
    цем
    0.35
    Activations Density 0.335%

    No Known Activations