© 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. 7107
    Prev
    Next
    INDEX
    Explanations

    instructions related to monitoring and staying involved in a situation

    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
     فريبيس
    -0.60
    httphttps
    -0.45
    esgue
    -0.40
     transfieras
    -0.37
    AsUp
    -0.37
    WebMethod
    -0.37
    OkHttpClient
    -0.36
     puits
    -0.36
    StoreMessageInfo
    -0.35
    lotl
    -0.35
    POSITIVE LOGITS
     watch
    2.33
    watch
    1.99
     Watch
    1.98
     WATCH
    1.81
    Watch
    1.80
     watches
    1.61
     watching
    1.59
    WATCH
    1.55
     watched
    1.54
     lookout
    1.51
    Activations Density 0.229%

    No Known Activations