© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    points of high impact in a process narrative

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

    Sentences followed by conjunctive adverbs

    np_acts-logits-general · gemini-2.0-flash

    additional connecting words

    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
     pinulongan
    -0.70
    ícil
    -0.64
     keiner
    -0.62
    ByVersion
    -0.58
    jsonwebtoken
    -0.55
    wapV
    -0.54
    URIComponent
    -0.54
     keinem
    -0.52
     Viitattu
    -0.52
    راتيج
    -0.50
    POSITIVE LOGITS
     also
    2.72
     additionally
    2.46
    Additionally
    2.42
    Also
    2.41
     Also
    2.40
     furthermore
    2.38
     Additionally
    2.38
    also
    2.36
     moreover
    2.28
    Furthermore
    2.27
    Activations Density 0.551%

    No Known Activations