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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 11245
    Prev
    Next
    INDEX
    Explanations

    terms related to aquatic life and related biological concepts

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

    bodies of water

    np_acts-logits-general · gemini-2.0-flash

    river mouth and estuaries

    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
    niſſe
    -0.79
    tagHelperRunner
    -0.78
    MLLoader
    -0.75
    ロウィン
    -0.74
    Manbalar
    -0.73
     Савезне
    -0.72
     queſta
    -0.71
    ☫
    -0.71
     $_(
    -0.71
     kasarigan
    -0.71
    POSITIVE LOGITS
    向
    0.30
     saumon
    0.27
     ríos
    0.26
    Xaml
    0.26
     river
    0.25
     salmon
    0.22
     tatlı
    0.21
     dulce
    0.20
    Hinweise
    0.20
     向
    0.20
    Activations Density 0.326%

    No Known Activations