© 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. 20-GEMMASCOPE-RES-16K
    11. 14961
    Prev
    Next
    INDEX
    Explanations

    phrases associated with adhesive properties and surface treatments

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

    Properties or actions related to coatings/adhesives

    np_acts-logits-general · gemini-2.0-flash

    material properties and applications

    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
    LookAnd
    -0.30
     graduación
    -0.27
    ือน
    -0.27
     CanadaChoose
    -0.27
     here
    -0.27
     graduation
    -0.26
     partag
    -0.25
     prédio
    -0.24
     favor
    -0.24
    Here
    -0.24
    POSITIVE LOGITS
     يتيمه
    0.74
     BoxFit
    0.69
    msgTypes
    0.68
    gonic
    0.66
    featureID
    0.61
    Kool
    0.59
     препратки
    0.59
     <<<<<<<<<<<<<<
    0.59
     AssemblyCulture
    0.59
    orianCalendar
    0.57
    Activations Density 0.155%

    No Known Activations