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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15414
    Prev
    Next
    INDEX
    Explanations

    references to specific property features and attributes

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

    Non-alphanumeric characters and math symbols

    np_acts-logits-general · gemini-2.0-flash

    recent or nearby locations

    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
    ſelf
    -0.83
     Efq
    -0.81
     Theſe
    -0.81
    ^(@)
    -0.78
     myſelf
    -0.69
     Beſ
    -0.69
     becauſe
    -0.68
     ſhould
    -0.67
    ILDREN
    -0.67
     whoſe
    -0.66
    POSITIVE LOGITS
     &
    0.68
     recently
    0.63
    contentLoaded
    0.58
     
    0.57
    ########.
    0.55
    Recently
    0.52
    !
    0.51
     +
    0.51
    <eos>
    0.50
     recent
    0.49
    Activations Density 0.022%

    No Known Activations