© 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. 24-GEMMASCOPE-RES-16K
    11. 5428
    Prev
    Next
    INDEX
    Explanations

    complex descriptive phrases related to perception and existential concepts

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

    describing qualities or importance

    np_acts-logits-general · gemini-2.0-flash

    German, Danish, and Dutch words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agerie
    -0.73
     harem
    -0.68
     sidekick
    -0.66
     ambigu
    -0.66
     smog
    -0.65
     acrob
    -0.65
     superpowers
    -0.64
     dandy
    -0.64
     backstory
    -0.63
     profan
    -0.63
    POSITIVE LOGITS
    faßt
    0.40
     groote
    0.34
     ausges
    0.34
     skall
    0.33
     zijne
    0.32
     formule
    0.32
    UserScript
    0.30
     politie
    0.29
     setEmail
    0.29
     imprese
    0.29
    Activations Density 0.731%

    No Known Activations