© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9316
    Prev
    Next
    INDEX
    Explanations

    various web URLs and hyperlinks within the text

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

    URLs starting with "http" or "https"

    np_acts-logits-general · gemini-2.0-flash

    http urls

    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
    nodoc
    -0.69
     ProtoMessage
    -0.69
    RUnlock
    -0.66
    homonymie
    -0.64
    PhysRevD
    -0.62
    MockBean
    -0.60
    pyplot
    -0.60
     صوتيه
    -0.57
     préfé
    -0.57
     télécommande
    -0.57
    POSITIVE LOGITS
     lenker
    0.56
    tschaft
    0.46
    nissen
    0.44
    tene
    0.44
    dstuk
    0.44
    leneck
    0.44
     lebens
    0.44
    HtmlAttribute
    0.44
     attest
    0.44
     Serial
    0.43
    Activations Density 0.088%

    No Known Activations