© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7199
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "for" in a document

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

    "for example" or "for instance"

    np_acts-logits-general · gemini-2.0-flash

    for example or instance

    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
    such
    -0.63
    راتيج
    -0.59
    Such
    -0.58
     parlent
    -0.57
     such
    -0.54
     veille
    -0.53
     Such
    -0.53
    Something
    -0.48
     Something
    -0.48
     SUCH
    -0.47
    POSITIVE LOGITS
     example
    2.04
     instance
    1.62
    example
    1.42
     examples
    1.36
     ejemplo
    1.30
     exemplo
    1.25
     exemple
    1.22
     Example
    1.22
     EXAMPLE
    1.19
    instance
    1.18
    Activations Density 0.111%

    No Known Activations