© 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. 20-GEMMASCOPE-RES-16K
    11. 7285
    Prev
    Next
    INDEX
    Explanations

    HTML-like syntax and attributes in markup language

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

    Strings inside XML name attributes

    np_acts-logits-general · gemini-2.0-flash

    string attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.53
    GeneratedCode
    -0.52
     متعلقه
    -0.50
    JsonFormat
    -0.49
     hashlib
    -0.49
    #+#
    -0.48
     calendriers
    -0.48
    TRAILING
    -0.47
    +#+
    -0.47
    رشف
    -0.47
    POSITIVE LOGITS
    :][
    0.60
    eseorang
    0.57
     attribute
    0.57
    celotti
    0.54
    ORUM
    0.53
    AGES
    0.52
     kepad
    0.51
     Attributes
    0.49
    šanās
    0.49
     оригіналу
    0.49
    Activations Density 0.061%

    No Known Activations