© 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. 40-GEMMASCOPE-RES-16K
    11. 7683
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific research, particularly focusing on biological and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sapato
    -0.44
    +#+
    -0.40
     tartalomajánló
    -0.40
    openzeppelin
    -0.40
    äge
    -0.37
     Theſe
    -0.37
    webElement
    -0.37
    fjspx
    -0.35
     Reſ
    -0.35
    ngdoc
    -0.35
    POSITIVE LOGITS
     body
    4.09
    body
    3.50
     Body
    3.47
    Body
    3.34
     BODY
    3.31
     bodies
    3.28
    BODY
    2.95
     cuerpo
    2.81
     Bodies
    2.80
    bodies
    2.66
    Activations Density 1.228%

    No Known Activations