© 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. 14-GEMMASCOPE-RES-16K
    11. 7994
    Prev
    Next
    INDEX
    Explanations

    instances of dialog-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     présidenti
    -0.50
     prevención
    -0.49
     Gestión
    -0.48
     médecine
    -0.46
    envoi
    -0.45
     bénéfice
    -0.45
     continente
    -0.44
    envoyer
    -0.44
    Russia
    -0.43
     capteur
    -0.43
    POSITIVE LOGITS
     dialog
    1.03
     Dialog
    0.99
    dialog
    0.98
    Dialog
    0.95
     DIALOG
    0.91
     MatDialog
    0.85
    dialogs
    0.81
     Dialogue
    0.81
     dialogue
    0.76
    DIALOG
    0.76
    Activations Density 0.174%

    No Known Activations