© 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. 22-GEMMASCOPE-RES-16K
    11. 329
    Prev
    Next
    INDEX
    Explanations

    file paths and programming syntax elements

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

    Code diffs referring to source files

    np_acts-logits-general · gemini-2.0-flash

    source code paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pepper
    -0.61
     Gruber
    -0.61
     Shum
    -0.58
     Lick
    -0.58
     Pen
    -0.57
     Zim
    -0.57
     Sim
    -0.57
     Carol
    -0.56
     Bah
    -0.56
     PEP
    -0.56
    POSITIVE LOGITS
     src
    2.01
    src
    1.97
    Src
    1.76
     Src
    1.62
     SRC
    1.58
    SRC
    1.48
     Sour
    1.15
    Sour
    1.11
    dst
    1.09
    srcs
    1.08
    Activations Density 0.262%

    No Known Activations