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. 16-GEMMASCOPE-RES-16K
    6. 6462
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities, particularly names and places

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

    Follows a capitalized abbreviation

    np_acts-logits-general · gemini-2.0-flash

    play based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.71
     itſelf
    -0.70
     myſelf
    -0.69
    UserScript
    -0.68
    Rüyada
    -0.64
    énario
    -0.63
     betweenstory
    -0.61
    شهاد
    -0.60
     Theſe
    -0.59
     Мексичка
    -0.59
    POSITIVE LOGITS
     kanssa
    0.72
    との
    0.63
     counterpart
    0.50
     whom
    0.47
     counterparts
    0.47
     partner
    0.46
    WebMethod
    0.44
     compreensão
    0.44
     vois
    0.44
    '
    0.43
    Activations Density 0.440%

    No Known Activations