© 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 EvalsExportsinterp-engineNEWAPI 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. 10856
    Prev
    Next
    INDEX
    Explanations

    numeric information related to statistics and measurements

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

    after periods, "and," "has," or "is"

    np_acts-logits-general · gemini-2.0-flash

    company role or action

    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
     Located
    -0.83
     located
    -0.79
    Located
    -0.78
    Hentet
    -0.74
     locating
    -0.69
    located
    -0.67
     locate
    -0.66
    antaranya
    -0.66
    位于
    -0.66
     poffible
    -0.65
    POSITIVE LOGITS
     Com
    0.52
    #+#
    0.48
     Kom
    0.47
    Com
    0.47
     therein
    0.46
     com
    0.45
     COM
    0.45
     туда
    0.43
     there
    0.43
     Pro
    0.42
    Activations Density 0.269%

    No Known Activations