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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3694
    Prev
    Next
    INDEX
    Explanations

    geographic locations and names of islands

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

    Chromosomes or islands

    np_acts-logits-general · gemini-2.0-flash

    geographical locations and chromosomes

    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
     Administrativna
    -0.58
    醐
    -0.56
    HandlerContext
    -0.52
    iNdEx
    -0.51
     <=",
    -0.50
    plish
    -0.50
     gräns
    -0.48
     kaarangay
    -0.48
    ỡng
    -0.48
    Pacific
    -0.47
    POSITIVE LOGITS
     island
    0.71
     Island
    0.66
     continent
    0.65
     ISLAND
    0.58
    Island
    0.56
    ChildScrollView
    0.56
    island
    0.53
     mainland
    0.52
    岛
    0.52
     continents
    0.50
    Activations Density 0.341%

    No Known Activations