© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4369
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery and mechanical functions

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

    after activating tokens

    np_acts-logits-general · gemini-2.0-flash

    shut-off switch, flash lamp, mold, connected windings

    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
    haviors
    -0.75
     squishy
    -0.71
     blurry
    -0.70
     tarmac
    -0.69
     velcro
    -0.67
     ponytail
    -0.67
     origami
    -0.66
     sorbet
    -0.66
     muffins
    -0.66
     infinites
    -0.64
    POSITIVE LOGITS
     skall
    0.53
     setempat
    0.51
     inspección
    0.45
     adecuado
    0.45
     adecuados
    0.44
     adecuadas
    0.44
     peralatan
    0.43
     erforder
    0.41
     wyma
    0.41
     required
    0.41
    Activations Density 1.664%

    No Known Activations