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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5942
    Prev
    Next
    INDEX
    Explanations

    references to space missions and astronomical studies

    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
     Hyde
    -0.47
    Hyde
    -0.45
    sizeCache
    -0.44
     Bully
    -0.43
     Vise
    -0.43
    reactstrap
    -0.43
     Curran
    -0.42
     Lach
    -0.40
     مشين
    -0.40
    shund
    -0.40
    POSITIVE LOGITS
     planets
    1.69
     NASA
    1.69
     astronomers
    1.64
     Space
    1.62
     astronauts
    1.56
     astronomy
    1.56
     Planets
    1.56
    NASA
    1.55
     spacecraft
    1.53
     astronomer
    1.52
    Activations Density 1.426%

    No Known Activations