© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12802
    Prev
    Next
    INDEX
    Explanations

    words and terms related to hydrogels and hydrophobic materials

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

    "Hydro" or related terms ("hyd", "hydrophobic", "hydrants")

    np_acts-logits-general · gemini-2.0-flash

    hyd words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walkover
    -0.52
    ----</
    -0.50
     useAppContext
    -0.46
     kaarangay
    -0.46
    ByVersion
    -0.45
    +#+
    -0.45
     linkovi
    -0.44
    脚注の使い方
    -0.44
    ValueStyle
    -0.40
    帖最后由
    -0.40
    POSITIVE LOGITS
     Hyd
    0.74
     hydro
    0.73
     hyd
    0.70
    Hydro
    0.69
    Hyd
    0.68
     HYDRO
    0.67
     Hydro
    0.65
     гидро
    0.63
    Hydra
    0.62
     Hydra
    0.61
    Activations Density 0.121%

    No Known Activations