© 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. 15024
    Prev
    Next
    INDEX
    Explanations

    features related to community amenities and accessibility

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

    Proximity to amenities

    np_acts-logits-general · gemini-2.0-flash

    nearby locations and distances

    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
     InputDecoration
    -0.56
    AddTagHelper
    -0.53
     चीज़ों
    -0.51
    rungsseite
    -0.50
    protoimpl
    -0.48
    ReusableCell
    -0.48
    Personendaten
    -0.47
    asius
    -0.47
     CreateTagHelper
    -0.46
     Autorisations
    -0.46
    POSITIVE LOGITS
     nearby
    0.41
     readily
    0.39
     proximité
    0.38
    ⓘ
    0.37
    nocześnie
    0.36
    nearby
    0.35
     fácilmente
    0.35
     пору
    0.35
     naselje
    0.34
    easily
    0.33
    Activations Density 0.083%

    No Known Activations