© 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. 28-GEMMASCOPE-RES-16K
    11. 1235
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that indicate restrictions or requirements

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

    after "and"

    np_acts-logits-general · gemini-2.0-flash

    and if, and unless, and despite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []).
    -0.44
    ’.
    -0.41
     €.
    -0.40
    SharedCtor
    -0.39
    ).
    -0.38
    '].
    -0.38
    ')).
    -0.38
    ').
    -0.38
     }).
    -0.36
     tern
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.90
     assuming
    0.77
    assuming
    0.69
     knowing
    0.67
     considering
    0.66
     considerando
    0.65
     несмотря
    0.63
     despite
    0.62
     especially
    0.61
    ThroughAttribute
    0.60
    Activations Density 0.331%

    No Known Activations