© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4413
    Prev
    Next
    INDEX
    Explanations

    specific variable names or identifiers related to data structures or programming code

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

    Hexadecimal representations

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal data identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.51
     للاسماء
    -0.49
    MessageOf
    -0.45
    पया
    -0.44
    httphttps
    -0.42
    écou
    -0.42
    espejo
    -0.41
    newArrayList
    -0.41
     Erişim
    -0.41
     educativas
    -0.40
    POSITIVE LOGITS
     Brut
    0.45
     PCD
    0.44
    underland
    0.44
     Sd
    0.44
     Yard
    0.44
     TD
    0.43
    sd
    0.43
    md
    0.43
     Spend
    0.43
     Md
    0.43
    Activations Density 0.391%

    No Known Activations