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. 14772
    Prev
    Next
    INDEX
    Explanations

    key numerical metrics related to scores and leads in competitive contexts

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

    Being ahead or behind

    np_acts-logits-general · gemini-2.0-flash

    score lead or deficit

    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
    RTEE
    -0.54
     发表于
    -0.53
    WebMethod
    -0.53
     Vikipedi
    -0.52
     الرياضيه
    -0.52
     متعلقه
    -0.51
    antics
    -0.51
    Rhestr
    -0.50
    chluss
    -0.49
    ungsver
    -0.48
    POSITIVE LOGITS
    jsonwebtoken
    0.62
    outState
    0.61
    τιά
    0.57
    rungsseite
    0.55
    +#+#
    0.52
    PyErr
    0.51
     BoxFit
    0.49
     dianteira
    0.48
    stateProvider
    0.48
     typelib
    0.47
    Activations Density 0.151%

    No Known Activations