© 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. 14017
    Prev
    Next
    INDEX
    Explanations

    technical terms or keywords in programming or software contexts

    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
     MainAxisSize
    -0.60
     Wortes
    -0.49
     Preisen
    -0.49
    llavero
    -0.45
    requireNonNull
    -0.44
    izieren
    -0.43
     Worten
    -0.42
    InjectMocks
    -0.42
     onCreateView
    -0.42
    enumi
    -0.42
    POSITIVE LOGITS
    Становништво
    0.48
     Guar
    0.47
     Laden
    0.44
     Tra
    0.43
     tra
    0.42
     Bals
    0.41
     Dub
    0.41
     neutral
    0.41
     Ster
    0.40
     circuit
    0.40
    Activations Density 0.074%

    No Known Activations