© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2535
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to marine biology and research methodologies

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

    Deep sea or ocean floor environments

    np_acts-logits-general · gemini-2.0-flash

    deep sea floor organisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TokenNameLBRACE
    -0.50
     Administrativna
    -0.45
    clipboard
    -0.40
     فريبيس
    -0.40
    DIPSETTING
    -0.39
     Midland
    -0.39
    riwal
    -0.38
     censiti
    -0.38
    InitStruct
    -0.37
    rifuge
    -0.36
    POSITIVE LOGITS
     surla
    0.70
     seabed
    0.66
     underwater
    0.65
     Underwater
    0.58
     fathoms
    0.58
    underwater
    0.57
     coral
    0.54
    海底
    0.52
     reefs
    0.52
     kelp
    0.52
    Activations Density 0.367%

    No Known Activations