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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11499
    Prev
    Next
    INDEX
    Explanations

    technical language and precise definitions in various contexts

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

    Past-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    past tense actions regarding information/objects

    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
    ValueStyle
    -0.79
    rungsseite
    -0.73
    GEBURTSDATUM
    -0.69
     effectually
    -0.67
    migrationBuilder
    -0.66
     systematically
    -0.65
     freely
    -0.64
     quietly
    -0.63
     regularly
    -0.63
     selectively
    -0.63
    POSITIVE LOGITS
     המצ
    0.32
     throughout
    0.32
     (>
    0.31
    jangkau
    0.31
     indeed
    0.30
    kasten
    0.30
     absorción
    0.30
     propOrder
    0.29
     Vikipedi
    0.29
     Bad
    0.28
    Activations Density 0.611%

    No Known Activations