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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3917
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or entities in the context of law or societal issues

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

    "The" followed by a concept/topic

    np_acts-logits-general · gemini-2.0-flash

    the followed by factual 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
     transfieras
    -0.44
    TintMode
    -0.43
     plate
    -0.41
     Marquette
    -0.40
     gynhyrchwyd
    -0.40
     Dragon
    -0.39
     Hopper
    -0.38
     GreatSchools
    -0.37
     nu
    -0.37
     Victor
    -0.36
    POSITIVE LOGITS
     fact
    0.71
     Tatsache
    0.70
     faptul
    0.62
     presencia
    0.61
     hecho
    0.60
     presenza
    0.59
     absence
    0.57
     presença
    0.57
     aanwezig
    0.57
     presence
    0.56
    Activations Density 0.711%

    No Known Activations