© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 13861
    Prev
    Next
    INDEX
    Explanations

    terms related to occupational and procedural contexts, specifically focusing on classifications and types of structures or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and abbreviations starting with "Oc" or "Occ" (such as "Octet", "Occluded", "Occupational").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.43
    labus
    -0.39
     mouseClicked
    -0.38
     grecque
    -0.38
    fjspx
    -0.37
    ismuth
    -0.36
    trm
    -0.35
     Luisa
    -0.35
    Tall
    -0.35
     Normdatei
    -0.35
    POSITIVE LOGITS
     Oc
    0.72
     Occ
    0.69
     OCC
    0.68
    Oc
    0.60
    OCC
    0.60
    Occ
    0.57
     oc
    0.56
     occ
    0.56
    tober
    0.54
     OCCUP
    0.53
    Activations Density 0.258%

    No Known Activations