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. 15-GEMMASCOPE-RES-16K
    6. 5231
    Prev
    Next
    INDEX
    Explanations

    different types of headwear or roofing materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    licts
    -0.62
    PECT
    -0.61
    flows
    -0.59
     Nagar
    -0.59
     Yaman
    -0.59
    //
    -0.58
     Fluids
    -0.58
     Flows
    -0.58
     flows
    -0.58
    GRAM
    -0.57
    POSITIVE LOGITS
     hats
    1.31
     Hats
    1.14
     hat
    1.12
    Hats
    1.10
     roof
    1.09
    Hat
    1.08
     Hat
    1.08
     roofs
    1.06
     cappello
    1.05
     Roof
    1.02
    Activations Density 0.244%

    No Known Activations