© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6861
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals or experts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.30
     rôles
    -0.24
    schrank
    -0.23
     titres
    -0.23
     opiniones
    -0.22
     secciones
    -0.22
     shoots
    -0.22
    #+#
    -0.21
    schuhe
    -0.21
    <bos>
    -0.20
    POSITIVE LOGITS
    etc
    0.83
    therefore
    0.80
    untuk
    0.77
    얻
    0.77
    wurde
    0.76
    again
    0.75
    adalah
    0.75
     queſta
    0.75
    also
    0.74
    and
    0.74
    Activations Density 4.986%

    No Known Activations