© 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. 8476
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to rules, regulations, and prescriptions

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

    Followed by "for" or "."

    np_acts-logits-general · gemini-2.0-flash

    months, Germans, states, evidence

    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
     تضيفلها
    -0.91
    principalTable
    -0.81
    setVerticalGroup
    -0.73
     '\\;'
    -0.71
    MigrationBuilder
    -0.70
    Autoritní
    -0.69
    OGND
    -0.66
     المعيارى
    -0.63
    ArrowToggle
    -0.63
     ModelExpression
    -0.62
    POSITIVE LOGITS
     syndrome
    0.73
     approach
    0.72
     method
    0.62
    ™
    0.60
     report
    0.60
     technique
    0.58
    audiovisuel
    0.56
     trope
    0.55
     workshop
    0.55
     question
    0.53
    Activations Density 0.656%

    No Known Activations