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. 1-GEMMASCOPE-RES-16K
    6. 6952
    Prev
    Next
    INDEX
    Explanations

    names of individuals and associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jeremy
    -0.65
     Jake
    -0.63
     Josh
    -0.60
    xtick
    -0.60
    Jeremy
    -0.60
     Liam
    -0.60
     Ethan
    -0.57
    scrollLeft
    -0.57
     Darren
    -0.57
    }();
    -0.56
    POSITIVE LOGITS
     actresses
    1.25
     actress
    1.19
     Elizabeth
    1.12
     goddess
    1.05
     princess
    1.02
    Elizabeth
    1.02
     goddesses
    1.00
     feminist
    1.00
     heroine
    0.99
     Susan
    0.99
    Activations Density 1.969%

    No Known Activations