© 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. 20-GEMMASCOPE-RES-16K
    11. 14045
    Prev
    Next
    INDEX
    Explanations

    measurements and specifications related to buildings and areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    kannt
    -0.31
     Deckel
    -0.30
    engesch
    -0.30
    timbangan
    -0.30
    KeyName
    -0.29
     calendriers
    -0.28
    Folder
    -0.28
    geschäft
    -0.28
    écart
    -0.28
     egyszer
    -0.27
    POSITIVE LOGITS
     autorytatywna
    0.74
    MigrationBuilder
    0.70
     فريبيس
    0.68
     Audiodateien
    0.68
     onCreateView
    0.67
     invokingState
    0.66
    IntoConstraints
    0.65
     صوتيه
    0.64
    awtextra
    0.63
    UrlResolution
    0.63
    Activations Density 0.072%

    No Known Activations