© 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
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 2164
    Prev
    Next
    INDEX
    Explanations

    references to signal strength and characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itiés
    -0.34
    multer
    -0.32
     dedicated
    -0.31
     dedicado
    -0.30
     LOADING
    -0.30
    enangan
    -0.29
     quiera
    -0.28
     Colomb
    -0.28
     сцен
    -0.28
     formerly
    -0.28
    POSITIVE LOGITS
    msgTypes
    0.69
     nakalista
    0.61
    AnchorStyles
    0.60
    GEBURTSDATUM
    0.59
     ligiloj
    0.59
    Välislingid
    0.58
    PreferredItem
    0.57
     الرياضيه
    0.57
     Signal
    0.57
    Географиясе
    0.56
    Activations Density 0.255%

    No Known Activations