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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4785
    Prev
    Next
    INDEX
    Explanations

    content related to scientific research and findings, particularly those that involve genetic studies and evolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.61
    msgTypes
    -0.52
    webElementGuid
    -0.50
     Part
    -0.50
    aysia
    -0.49
    rowave
    -0.48
    inerja
    -0.48
    javadoc
    -0.45
    нома
    -0.45
    InitStruct
    -0.45
    POSITIVE LOGITS
    Nature
    0.75
     Nature
    0.74
    nature
    0.68
     nature
    0.67
    PhysRevLett
    0.67
     Science
    0.64
     NATURE
    0.63
    Science
    0.63
     science
    0.63
    NATURE
    0.61
    Activations Density 0.779%

    No Known Activations