© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3215
    Prev
    Next
    INDEX
    Explanations

    abbreviations and symbols related to scientific measurements and parameters

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

    academic citation references and file formatting codes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    citation references and academic paper formatting codes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uits
    -0.43
     setTimeout
    -0.42
    jenost
    -0.40
    قایناقلار
    -0.40
     reality
    -0.40
    PositiveButton
    -0.40
    WriteTagHelper
    -0.39
    ByPrimaryKey
    -0.38
    ilane
    -0.37
    ilhas
    -0.37
    POSITIVE LOGITS
     transfieras
    0.50
    canestro
    0.48
    ArgsConstructor
    0.45
    Slf
    0.44
    httphttps
    0.44
    mybatisplus
    0.42
    PyExc
    0.42
    ukone
    0.42
    Transkript
    0.41
    ragan
    0.41
    Activations Density 0.410%

    No Known Activations