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. 24-GEMMASCOPE-RES-16K
    6. 12657
    Prev
    Next
    INDEX
    Explanations

    references to family members and relationships

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

    Tokens after capitalized names

    np_acts-logits-general · gemini-2.0-flash

    words preceding punctuation or endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    IActionResult
    -0.58
     /*#__
    -0.48
    Américaine
    -0.46
     ExecuteAsync
    -0.45
    openzeppelin
    -0.44
     Sơ
    -0.44
    skraft
    -0.43
     Quý
    -0.42
     refroidissement
    -0.42
    🏾
    -0.41
    POSITIVE LOGITS
     Madison
    0.77
     يتيمه
    0.73
     utafitiHapana
    0.72
     Sydney
    0.71
    Mad
    0.71
     Mad
    0.69
    Madison
    0.69
     Madi
    0.68
     Maddie
    0.67
    Sydney
    0.67
    Activations Density 0.052%

    No Known Activations