© 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. 7-GEMMASCOPE-RES-16K
    11. 15918
    Prev
    Next
    INDEX
    Explanations

    greetings and polite expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     celebración
    -0.38
     gotta
    -0.35
     judiciaire
    -0.35
     libremente
    -0.35
    oarece
    -0.35
     industriales
    -0.35
     observación
    -0.34
     propios
    -0.33
    İstinadlar
    -0.33
     desmotivaciones
    -0.33
    POSITIVE LOGITS
    Здравствуйте
    0.82
    Bonjour
    0.82
    Greetings
    0.81
    Cześć
    0.80
    Witam
    0.79
    дравствуйте
    0.77
    Coucou
    0.76
     Greetings
    0.76
     Bonjour
    0.76
    Bonsoir
    0.76
    Activations Density 0.182%

    No Known Activations