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

    Neuronpedia

    Jacobian LensNEW
    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. 14003
    Prev
    Next
    INDEX
    Explanations

    signals related to processing data in a technical or computational context

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

    Followed by usage or control

    np_acts-logits-general · gemini-2.0-flash

    then subsequently later

    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
    évaluateur
    -0.71
     Италијани
    -0.70
    Ārējās
    -0.59
     transfieras
    -0.59
    TagMode
    -0.59
     ddelweddau
    -0.58
    IntoConstraints
    -0.58
     initWithFrame
    -0.57
    Personendaten
    -0.56
    ILayout
    -0.56
    POSITIVE LOGITS
     further
    0.88
     subsequently
    0.88
     then
    0.88
     vidare
    0.88
     subsequent
    0.86
    further
    0.85
     vervolgens
    0.84
    then
    0.82
     затем
    0.81
     later
    0.80
    Activations Density 0.853%

    No Known Activations