Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15644
    Prev
    Next
    INDEX
    Explanations

    references to various types of fish and seafood dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.49
    rebbero
    -0.45
    ampton
    -0.45
    istoitu
    -0.44
    Παραπομπές
    -0.43
    іод
    -0.43
     hoogte
    -0.43
    ****/
    -0.43
    verwijspagina
    -0.42
     Kno
    -0.42
    POSITIVE LOGITS
     fish
    1.96
    Fish
    1.81
     Fish
    1.81
    fish
    1.64
     FISH
    1.61
    FISH
    1.52
     fishes
    1.49
     fished
    1.37
     poissons
    1.36
    fishes
    1.35
    Activations Density 0.219%

    No Known Activations