© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4114
    Prev
    Next
    INDEX
    Explanations

    phrases related to a call-to-action or various forms of engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtand
    -0.39
     giudi
    -0.39
     brewed
    -0.38
    setArguments
    -0.38
     embroidered
    -0.38
     huur
    -0.37
     hanged
    -0.37
     poffible
    -0.36
     peeled
    -0.36
     reconciled
    -0.36
    POSITIVE LOGITS
     tagging
    1.08
     taping
    1.03
     chaining
    1.02
    oning
    0.99
    framing
    0.98
     charting
    0.96
    indexing
    0.96
     framing
    0.96
     threading
    0.96
    encing
    0.96
    Activations Density 2.311%

    No Known Activations