© 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. 22-GEMMASCOPE-RES-16K
    11. 12620
    Prev
    Next
    INDEX
    Explanations

    genetic references, particularly related to genes and mutations affecting conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fortn
    -0.40
     jsPsych
    -0.38
     tapaht
    -0.37
     tekem
    -0.37
    IsMutable
    -0.36
    PTP
    -0.35
    fillType
    -0.33
     történ
    -0.33
     løpet
    -0.33
     propOrder
    -0.33
    POSITIVE LOGITS
     genes
    0.68
     gene
    0.63
    encoding
    0.53
    MLLoader
    0.52
    genes
    0.50
    基因
    0.49
     encoding
    0.49
     Cardoso
    0.49
    coding
    0.47
     MonoBehaviour
    0.47
    Activations Density 1.933%

    No Known Activations