© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2453
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data processing and indexing

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

    technical and scientific terminology, particularly from academic papers and research documents.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ReusableCell
    -0.65
    étoit
    -0.63
     للمعارف
    -0.57
    躇
    -0.56
     RIPRODUZIONE
    -0.56
    SaveChanges
    -0.55
    animaux
    -0.54
    prnewswire
    -0.54
    aucune
    -0.54
     powied
    -0.54
    POSITIVE LOGITS
     I
    0.69
     i
    0.65
    I
    0.64
     in
    0.57
     IN
    0.57
    isIn
    0.56
     Ii
    0.54
     Ink
    0.54
     Inoue
    0.53
    in
    0.53
    Activations Density 0.960%

    No Known Activations