© 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. 34-GEMMASCOPE-RES-16K
    11. 410
    Prev
    Next
    INDEX
    Explanations

    terms related to "head" and its variations, particularly in the context of health and anatomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.51
     Grüsse
    -0.35
     समीक्षाओं
    -0.35
    Rhestr
    -0.34
     싶
    -0.34
    uxxxx
    -0.33
     peores
    -0.33
     reformas
    -0.32
    μβρίου
    -0.32
     arbres
    -0.31
    POSITIVE LOGITS
     Head
    0.96
    Head
    0.92
     head
    0.85
     HEAD
    0.83
    head
    0.77
    quartered
    0.74
    HEAD
    0.74
     ヘッド
    0.71
    quarter
    0.71
     Heads
    0.71
    Activations Density 0.102%

    No Known Activations