© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1350
    Prev
    Next
    INDEX
    Explanations

    objects, their properties, and associated actions or commands

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

    following a verb/noun

    np_acts-logits-general · gemini-2.0-flash

    into, onto, accordingly

    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
    AnimationsModule
    -0.73
    IsMutable
    -0.72
    oredCriteria
    -0.66
    outSlope
    -0.66
    ionali
    -0.66
    GOTREF
    -0.65
     otomatig
    -0.65
     consultato
    -0.63
     continuant
    -0.63
    aneity
    -0.61
    POSITIVE LOGITS
     into
    1.09
     adecuadamente
    0.71
     onto
    0.70
    into
    0.64
     accordingly
    0.63
    ให้
    0.61
     anew
    0.61
    ให
    0.60
     appropriately
    0.60
     differently
    0.59
    Activations Density 0.908%

    No Known Activations