Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11583
    Prev
    Next
    INDEX
    Explanations

    elements related to server connection and API configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viking
    -0.38
    NavController
    -0.36
     gruppen
    -0.36
    Fach
    -0.35
    ༘
    -0.35
    :✨
    -0.33
     contrô
    -0.33
     autorytatywna
    -0.33
     Poids
    -0.32
     CONTROLS
    -0.32
    POSITIVE LOGITS
     environment
    0.80
     env
    0.77
     production
    0.77
    production
    0.75
     Environment
    0.74
    Environment
    0.73
    env
    0.73
    environment
    0.73
    AccessorTable
    0.69
     Production
    0.69
    Activations Density 0.256%

    No Known Activations