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. 25-GEMMASCOPE-RES-16K
    6. 3973
    Prev
    Next
    INDEX
    Explanations

    terms related to reproductive biology and pathogen interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lander
    -0.95
     Ringer
    -0.92
     Langer
    -0.92
     Wilder
    -0.92
     Ryder
    -0.89
     Rocker
    -0.87
    Binder
    -0.86
     Binder
    -0.86
     Hager
    -0.86
     Coder
    -0.86
    POSITIVE LOGITS
     Milne
    0.68
    Arc
    0.62
     Meade
    0.61
     Arc
    0.60
     Woolf
    0.56
     Arne
    0.55
    arc
    0.55
    arcs
    0.55
     Jayne
    0.54
     Barrington
    0.54
    Activations Density 2.230%

    No Known Activations