© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8337
    Prev
    Next
    INDEX
    Explanations

    technical terms related to surgical procedures and medical devices

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

    Methods of attaching or securing things

    np_acts-logits-general · gemini-2.0-flash

    fastening or securing mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.71
     فريبيس
    -0.64
     mills
    -0.60
    IntoConstraints
    -0.59
     Winaray
    -0.57
    PRA
    -0.56
    مصادر
    -0.56
    elemField
    -0.55
     yards
    -0.55
    tease
    -0.54
    POSITIVE LOGITS
     fastening
    0.71
     fasteners
    0.61
     fasten
    0.59
     fijar
    0.58
     securing
    0.57
     fixation
    0.55
    secure
    0.55
     Fix
    0.55
     covalent
    0.54
     tighten
    0.54
    Activations Density 0.385%

    No Known Activations