© 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. 40-GEMMASCOPE-RES-16K
    6. 1561
    Prev
    Next
    INDEX
    Explanations

    dishes and meals from a specific cuisine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     évêque
    -0.46
     tasche
    -0.45
     regole
    -0.45
     vœ
    -0.44
     fotógrafo
    -0.44
     notizie
    -0.43
     dones
    -0.43
     fotográfico
    -0.43
    wußt
    -0.43
     sourire
    -0.42
    POSITIVE LOGITS
     pay
    0.45
     Wikimedijinoj
    0.44
     air
    0.42
    Datuak
    0.42
    penup
    0.41
     rem
    0.40
    يكب
    0.40
    HideFlags
    0.39
     iris
    0.39
    lendir
    0.39
    Activations Density 0.113%

    No Known Activations