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. 4237
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or actions of a subject

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

    Followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    they followed by verb

    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
    hax
    -0.53
    tymologie
    -0.52
    جمعیت
    -0.51
    tois
    -0.50
    rouch
    -0.47
    yaxis
    -0.46
    vores
    -0.45
     Amin
    -0.45
     réussite
    -0.45
    OPE
    -0.44
    POSITIVE LOGITS
     protoimpl
    0.72
    ⓧ
    0.70
     fieldNum
    0.66
     ExecuteAsync
    0.66
     EconPapers
    0.66
     autorytatywna
    0.65
    ----</
    0.64
    aarrggbb
    0.63
    msgSender
    0.63
    Obrázky
    0.61
    Activations Density 0.273%

    No Known Activations