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. 114542
    Prev
    Next
    INDEX
    Explanations

    technical specifications and operational details related to computing structures

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

    Special characters and punctuation that serve as separators or delimiters in structured text like code, mathematical formulas, and data formats.

    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
    tagext
    -0.57
     Biôgrafia
    -0.53
    formik
    -0.51
     ExecuteAsync
    -0.48
    CodedInputStream
    -0.47
    TargetException
    -0.46
    FunctionFlags
    -0.45
    extAlignment
    -0.44
     IBOutlet
    -0.43
    MeasureSpec
    -0.43
    POSITIVE LOGITS
    Notae
    0.58
    principalTable
    0.55
    Autoritní
    0.54
    MessageTagHelper
    0.50
    richTextPanel
    0.49
     utafitiHapana
    0.49
    rungsseite
    0.48
    verifyException
    0.47
     referenties
    0.47
     Normdatei
    0.45
    Activations Density 2.535%

    No Known Activations