© 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. 12-GEMMASCOPE-RES-16K
    11. 10986
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns in numerical or alphanumeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.69
    帖最后由
    -0.63
     EconPapers
    -0.59
    twimg
    -0.57
    WriteTagHelper
    -0.56
     ReactDOM
    -0.55
    loroethene
    -0.54
     dial
    -0.52
    SourceChecksum
    -0.51
    koła
    -0.50
    POSITIVE LOGITS
     consultato
    0.75
    MLLoader
    0.64
     initWith
    0.62
    styleable
    0.59
    CJK
    0.55
    rilla
    0.54
     AssemblyTitle
    0.51
     <!--
    0.50
    êcher
    0.50
    initWith
    0.49
    Activations Density 0.113%

    No Known Activations