© 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. 8480
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and citations in research contexts

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

    Text within brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    academic publishers

    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
     ModelExpression
    -0.51
     Recu
    -0.45
    usermodel
    -0.45
     memo
    -0.45
    הערות
    -0.44
    JDBC
    -0.44
    uffff
    -0.44
    ⓧ
    -0.43
     Laughter
    -0.43
     napo
    -0.43
    POSITIVE LOGITS
     BoxDecoration
    0.75
     Normdatei
    0.71
     Springer
    0.71
     transfieras
    0.67
    Else
    0.66
     lenker
    0.66
     Academic
    0.64
    MemoryWarning
    0.63
    extAlignment
    0.62
     nonatomic
    0.62
    Activations Density 0.256%

    No Known Activations