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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1012
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts, particularly in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or interpolation points

    np_acts-logits-general · gemini-2.0-flash

    halfway point calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.59
    oneofs
    -0.50
     كومونز
    -0.49
    Външни
    -0.48
    Спасылкі
    -0.48
    __*/
    -0.48
     Jove
    -0.47
    Tikang
    -0.47
    SafeMath
    -0.46
    principalTable
    -0.46
    POSITIVE LOGITS
     interpolated
    0.52
     midway
    0.52
     point
    0.50
    interp
    0.50
     halfway
    0.49
     midpoint
    0.47
    Interpolation
    0.47
     peak
    0.47
     tại
    0.46
    interpolation
    0.46
    Activations Density 1.261%

    No Known Activations