© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15606
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific research and methodologies

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

    Papers' and studies' topic introductions

    np_acts-logits-general · gemini-2.0-flash

    reports/develops novel methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.71
    RuleContext
    -0.63
    yarnpkg
    -0.60
    LayoutConstraint
    -0.57
    FUT
    -0.56
    raisemb
    -0.54
    weder
    -0.53
    ambilan
    -0.53
    ríamos
    -0.53
    hoeddwyd
    -0.52
    POSITIVE LOGITS
     methodology
    0.90
     developed
    0.90
     technique
    0.86
     method
    0.84
     novel
    0.83
    method
    0.77
     develop
    0.74
    novel
    0.74
    developed
    0.72
    Method
    0.71
    Activations Density 1.192%

    No Known Activations