© 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. 8-GEMMASCOPE-RES-16K
    11. 6374
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with detection methodologies and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Empres
    -0.50
     personalización
    -0.43
     année
    -0.42
     stället
    -0.41
     gü
    -0.41
    lendir
    -0.41
     restent
    -0.40
     año
    -0.40
    jadikan
    -0.40
     Socialista
    -0.39
    POSITIVE LOGITS
     detection
    2.23
     detect
    2.17
     Detection
    2.09
     Detect
    2.06
     detecting
    1.99
    detect
    1.97
     detected
    1.93
     detects
    1.88
    detection
    1.85
    Detection
    1.84
    Activations Density 0.203%

    No Known Activations