© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly authors or notable figures

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

    First part of capitalized names

    np_acts-logits-general · gemini-2.0-flash

    personal names

    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
    AndEndTag
    -0.77
    createCanvas
    -0.55
    setVerticalGroup
    -0.55
     remplir
    -0.53
    OVERALL
    -0.53
    myapplication
    -0.52
    دانشنامهٔ
    -0.51
    الحياه
    -0.50
    :✨
    -0.50
    EndTag
    -0.50
    POSITIVE LOGITS
     boun
    0.58
    ogenes
    0.53
    fried
    0.52
    zegorz
    0.52
     Quant
    0.51
    ("")]
    
    0.50
     dropper
    0.49
    ondas
    0.49
     herds
    0.48
     Lard
    0.48
    Activations Density 0.221%

    No Known Activations