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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15185
    Prev
    Next
    INDEX
    Explanations

    references to components and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.93
     HasFactory
    -0.91
    sizeCache
    -0.91
    NameInMap
    -0.88
     giudi
    -0.86
    GraphicsUnit
    -0.83
    umato
    -0.82
    pagestyle
    -0.80
     <>",
    -0.79
     nargin
    -0.79
    POSITIVE LOGITS
     components
    1.89
     component
    1.82
    components
    1.82
     Component
    1.73
     Components
    1.71
    Component
    1.70
    component
    1.70
     COMPONENT
    1.65
    Components
    1.58
    COMPONENT
    1.50
    Activations Density 0.034%

    No Known Activations