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. 18-GEMMASCOPE-RES-16K
    6. 10205
    Prev
    Next
    INDEX
    Explanations

    concepts related to sunlight exposure and temperature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormUrlEncoded
    -0.72
    TagMode
    -0.68
    ussis
    -0.56
    حوالہ
    -0.56
    @[+][
    -0.56
     urethra
    -0.55
    lably
    -0.55
    ])));
    -0.55
     cuff
    -0.54
    bellum
    -0.54
    POSITIVE LOGITS
     sun
    1.96
     sunlight
    1.93
     sunshine
    1.77
    sun
    1.65
    Sunlight
    1.61
     Sunlight
    1.61
     sunny
    1.55
     Sun
    1.50
     SUN
    1.45
    Sun
    1.44
    Activations Density 0.152%

    No Known Activations