© 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. 35-GEMMASCOPE-RES-16K
    11. 13156
    Prev
    Next
    INDEX
    Explanations

    words related to biological processes and conditions, particularly in the context of genetic and medical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adecimal
    -0.93
    amphetamine
    -0.88
    theless
    -0.84
    lihood
    -0.82
    voltaic
    -0.82
    ostante
    -0.81
    oporosis
    -0.79
    styrene
    -0.76
    sterious
    -0.75
    ſelf
    -0.73
    POSITIVE LOGITS
    NewUrlParser
    0.42
    reuung
    0.40
     Pourtant
    0.37
     Meski
    0.36
    Trả
    0.35
    aq
    0.33
     uLocal
    0.33
     Apesar
    0.32
     Berikut
    0.31
    Meski
    0.31
    Activations Density 1.691%

    No Known Activations