© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    instructions for preparation and cooking methods

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

    preference or suitability

    np_acts-logits-general · gemini-2.0-flash

    specifying adjective or noun

    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
    AppMethodBeat
    -0.43
    lapsingToolbar
    -0.36
    lossus
    -0.33
    instancetype
    -0.32
     Former
    -0.31
     tanto
    -0.30
     intakes
    -0.29
     초
    -0.28
     dirname
    -0.28
    شتر
    -0.28
    POSITIVE LOGITS
     preferably
    1.08
     suitable
    1.07
     geeigne
    0.94
    preferably
    0.93
    suitable
    0.93
    GEBURTSDATUM
    0.92
     Preferably
    0.90
     compatible
    0.86
     capable
    0.83
     подходя
    0.82
    Activations Density 0.708%

    No Known Activations