© 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. 2541
    Prev
    Next
    INDEX
    Explanations

    names and email addresses

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

    Email addresses

    np_acts-logits-general · gemini-2.0-flash

    email addresses

    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
    ."));
    -1.27
    "]);
    -1.25
     }}$}
    -1.24
    "])
    -1.23
    ')))
    -1.22
    .")
    -1.21
    ")){
    -1.21
    ]")
    -1.19
    "):
    -1.19
    '))
    -1.19
    POSITIVE LOGITS
    @
    3.08
     @
    1.96
    (@
    1.52
    [@
    1.30
    ...@
    1.26
    @@
    1.23
    @[
    1.21
    .@
    1.20
    >@
    1.20
     '@
    1.19
    Activations Density 0.155%

    No Known Activations