© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116124
    Prev
    Next
    INDEX
    Explanations

    words related to marine animals, particularly sharks and whales.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @dribnet

    references to marine animals, particularly sharks and whales

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

    animals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.43
     Pre
    -0.42
    #--
    -0.39
     Cale
    -0.38
     F
    -0.38
    正
    -0.38
     New
    -0.37
     D
    -0.37
     d
    -0.36
    sü
    -0.36
    POSITIVE LOGITS
     enfans
    0.91
     plufieurs
    0.81
     ainfi
    0.80
     kapture
    0.74
    ihnach
    0.74
     desmotivaciones
    0.73
     Monfieur
    0.73
     vétérina
    0.70
    Shark
    0.70
     Shark
    0.67
    Activations Density 0.017%

    No Known Activations