© 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. 35-GEMMASCOPE-RES-16K
    11. 5023
    Prev
    Next
    INDEX
    Explanations

    terms related to devices and their functions in shooting or hunting contexts

    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
     Normdatei
    -0.42
     gitara
    -0.34
    QMetaType
    -0.33
    spesies
    -0.32
     reproducir
    -0.32
     catholique
    -0.32
    Fau
    -0.32
    fromnode
    -0.32
     charter
    -0.32
     Meta
    -0.32
    POSITIVE LOGITS
     sight
    0.80
     sights
    0.76
     Sight
    0.72
     Aim
    0.72
    sight
    0.72
    Aim
    0.69
    aim
    0.69
    Sight
    0.69
     aiming
    0.68
     aim
    0.67
    Activations Density 0.173%

    No Known Activations