© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    references to freshwater environments and organisms

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

    land, freshwater, or inland environments

    np_acts-logits-general · gemini-2.0-flash

    land, water, and associated entities

    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
    Linki
    -0.31
     nakalista
    -0.31
    tagHelperRunner
    -0.31
     préférence
    -0.30
    Ārējās
    -0.30
     flexibilidad
    -0.30
    dafx
    -0.29
     Är
    -0.27
    mLast
    -0.27
    onPressed
    -0.26
    POSITIVE LOGITS
     Inland
    0.82
     overland
    0.72
     terrestrial
    0.72
     terrestres
    0.72
     Terrestrial
    0.72
     inland
    0.68
     Overland
    0.68
     terrestre
    0.64
     Freshwater
    0.64
    陸上
    0.64
    Activations Density 0.432%

    No Known Activations