© 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. 35-GEMMASCOPE-RES-16K
    11. 12229
    Prev
    Next
    INDEX
    Explanations

    key concepts and theories related to human evolution and its complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.78
    KommentareTeilen
    -0.76
     CreateTagHelper
    -0.68
    contentLoaded
    -0.65
    IntoConstraints
    -0.64
    parsedMessage
    -0.62
     autorytatywna
    -0.61
    LOYEES
    -0.60
    Personensuche
    -0.58
    esModule
    -0.57
    POSITIVE LOGITS
     journalism
    1.20
     dentistry
    1.18
     agriculture
    1.15
     politics
    1.14
     Christianity
    1.05
     medicine
    1.03
     astronomy
    0.98
     psychiatry
    0.98
     photography
    0.96
     Judaism
    0.95
    Activations Density 1.386%

    No Known Activations