© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5512
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests or confirmations in a context involving support or assistance

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

    Slavic languages and romanizations

    np_acts-logits-general · gemini-2.0-flash

    Slavic languages and email/account verification

    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
    RenderAtEndOf
    -0.53
    ETHING
    -0.53
    DotNetBar
    -0.50
    esgue
    -0.49
     ***!
    -0.48
     cherchés
    -0.47
    cdnjs
    -0.47
    careous
    -0.46
    ونه
    -0.45
     EdgeInsets
    -0.45
    POSITIVE LOGITS
     ब्रेकडाउन
    0.66
    fjspx
    0.63
    Xna
    0.60
    WriteTagHelper
    0.59
     mergeFrom
    0.58
     Biôgrafia
    0.57
    ⓧ
    0.56
    CodedInputStream
    0.53
    ла
    0.53
     Gell
    0.52
    Activations Density 0.080%

    No Known Activations