© 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. 344
    Prev
    Next
    INDEX
    Explanations

    indicators of quality and evaluation in various contexts

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

    "for" and related capitalization

    np_acts-logits-general · gemini-2.0-flash

    for and its contexts

    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
    ts
    -0.38
     జ
    -0.34
    ätie
    -0.34
     спра
    -0.33
     aras
    -0.33
     gehört
    -0.33
    过
    -0.32
    asio
    -0.32
     huo
    -0.32
     gehören
    -0.32
    POSITIVE LOGITS
    FOR
    1.50
     For
    1.44
    For
    1.44
     FOR
    1.44
    for
    1.40
     snippetHide
    1.03
    ंदीखरीदारी
    0.99
    fjspx
    0.93
    ForAll
    0.91
    fora
    0.90
    Activations Density 0.688%

    No Known Activations