© 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. 3029
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to microscopy and sample preparation

    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
    featureID
    -0.58
     iconTwitter
    -0.54
    scout
    -0.52
    SPELL
    -0.50
    spell
    -0.48
    STALK
    -0.48
    sher
    -0.48
    sauce
    -0.47
    stig
    -0.47
     ſtand
    -0.47
    POSITIVE LOGITS
     SL
    2.22
     slide
    2.19
     슬
    2.08
     Slide
    2.02
     slides
    1.95
     sl
    1.93
    SL
    1.90
     sli
    1.88
     slip
    1.88
     Sli
    1.87
    Activations Density 1.302%

    No Known Activations