© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14681
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and coding processes

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

    sequence or order

    np_acts-logits-general · gemini-2.0-flash

    order and sequence

    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
    RectangleBorder
    -0.57
    GraphicsUnit
    -0.55
    illable
    -0.50
    XmlAccessType
    -0.50
     contextLoads
    -0.48
    Trama
    -0.47
     externi
    -0.47
    分に
    -0.47
    broek
    -0.47
    lès
    -0.46
    POSITIVE LOGITS
     precede
    1.03
     preceded
    0.97
     after
    0.94
     muna
    0.91
     first
    0.90
     Reihenfolge
    0.89
     precedes
    0.89
    pierw
    0.88
     skipped
    0.88
     сначала
    0.88
    Activations Density 0.933%

    No Known Activations