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. 15028
    Prev
    Next
    INDEX
    Explanations

    technical terms and versions associated with Android support libraries

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

    Followed by specific words ("constraint", "math", "web", "Water")

    np_acts-logits-general · gemini-2.0-flash

    American Water Ski Association

    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
    ,
    -0.50
    Quick
    -0.47
     cepat
    -0.46
     warten
    -0.44
    зен
    -0.43
     snart
    -0.43
    tere
    -0.43
    feof
    -0.42
    >{@
    -0.42
     banheiro
    -0.42
    POSITIVE LOGITS
     InputDecoration
    0.89
     surla
    0.86
     snippetHide
    0.84
     BoxDecoration
    0.84
     MainAxisSize
    0.82
     autorytatywna
    0.74
    harusnya
    0.71
    tvguidetime
    0.70
    kuuta
    0.70
     arşivlendi
    0.69
    Activations Density 0.068%

    No Known Activations