© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11409
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſever
    -0.44
     queſta
    -0.43
    исленность
    -0.42
    jmniej
    -0.40
     geſ
    -0.40
    tonsoft
    -0.40
     resultMap
    -0.39
    ForValue
    -0.39
    SequentialGroup
    -0.39
    ğinde
    -0.39
    POSITIVE LOGITS
     inside
    0.73
    inside
    0.72
     dentro
    0.68
    Into
    0.67
    Inside
    0.66
    dentro
    0.66
     Into
    0.66
     into
    0.65
     Inside
    0.65
     INSIDE
    0.60
    Activations Density 0.305%

    No Known Activations