© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9658
    Prev
    Next
    INDEX
    Explanations

    instances of extreme conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Contactez
    -0.40
    msford
    -0.39
     québéco
    -0.39
    ":[{
    -0.36
    typen
    -0.36
    hithe
    -0.36
    ladies
    -0.36
    pido
    -0.35
    pollo
    -0.35
     fraî
    -0.35
    POSITIVE LOGITS
     дописавши
    0.58
    canestro
    0.57
    లాలు
    0.55
    úgó
    0.55
     nahilalakip
    0.54
     disambiguazione
    0.53
    Portail
    0.53
    SBATCH
    0.53
    basicConfig
    0.52
    Pyx
    0.52
    Activations Density 0.035%

    No Known Activations