© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5910
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their properties in programming contexts

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

    Class properties/members

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and assignments

    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
     
    -1.06
     a
    -0.97
     the
    -0.94
     “
    -0.92
     "
    -0.90
    <eos>
    -0.80
     all
    -0.79
     in
    -0.76
     ‘
    -0.72
     super
    -0.70
    POSITIVE LOGITS
    IntoConstraints
    1.13
     ―――――
    1.10
     itſelf
    1.09
     myſelf
    1.07
    WebVitals
    1.06
     Anſ
    1.05
     ſche
    1.03
     houſe
    1.03
    RenderAtEndOf
    1.03
     Monfieur
    1.02
    Activations Density 0.784%

    No Known Activations