© 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. 25-GEMMASCOPE-RES-16K
    11. 16345
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular processes and treatment effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     säll
    -0.44
     varandra
    -0.37
    StatusOK
    -0.37
     Cæsar
    -0.35
     skär
    -0.33
    nervous
    -0.33
     vaiz
    -0.33
     SPF
    -0.33
     Caesar
    -0.32
     Baccarat
    -0.32
    POSITIVE LOGITS
    ArgumentParser
    0.63
    orsese
    0.49
    outSlope
    0.49
     المعيارى
    0.48
     intervention
    0.48
     exposure
    0.48
    __(/*!
    0.48
     TREATMENT
    0.47
     combinación
    0.47
     supplementation
    0.46
    Activations Density 2.625%

    No Known Activations