© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3657
    Prev
    Next
    INDEX
    Explanations

    elements related to visual media, specifically videos and stock footage

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

    Tokens preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    specific terms followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whose
    -0.28
    execute
    -0.26
    ^-
    -0.26
     weigh
    -0.26
     unchanged
    -0.25
     Atlántico
    -0.25
     yourselves
    -0.25
     Dar
    -0.25
     taught
    -0.25
     Mit
    -0.25
    POSITIVE LOGITS
    rungsseite
    0.71
    AnchorStyles
    0.69
     Audiodateien
    0.64
    <unused23>
    0.63
    <unused47>
    0.63
    [@BOS@]
    0.63
    <unused68>
    0.63
    endpush
    0.63
    <unused14>
    0.63
    <unused16>
    0.63
    Activations Density 0.052%

    No Known Activations