© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    terms related to dryness and moisture in various contexts

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

    "dry" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    dry and drying states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlCommand
    -0.58
     lenker
    -0.56
    entan
    -0.54
    tableCell
    -0.51
    fortawesome
    -0.50
    VertexAttrib
    -0.50
     препратки
    -0.50
    OGND
    -0.50
     useDispatch
    -0.49
     Италијани
    -0.49
    POSITIVE LOGITS
     Dry
    1.21
     dry
    1.19
    Dry
    1.16
     dryness
    1.12
    dry
    1.02
     DRY
    1.02
     drier
    0.95
    Drying
    0.93
     Drying
    0.93
     drying
    0.92
    Activations Density 0.178%

    No Known Activations