© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7452
    Prev
    Next
    INDEX
    Explanations

    concepts related to mixing or mixture combinations

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

    the word "mix" or "mixed" followed by words indicating components being combined.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nanoTime
    -0.64
    Dermott
    -0.63
    urlopen
    -0.62
    noopener
    -0.60
    Facades
    -0.60
    defineProperty
    -0.59
     MainAxisSize
    -0.56
    fortawesome
    -0.55
     חיצוניים
    -0.54
    出版年
    -0.53
    POSITIVE LOGITS
     mix
    1.38
     Mix
    1.20
     MIX
    1.19
    Mix
    1.15
    mix
    1.15
     mixture
    1.15
     mixes
    1.13
     mixing
    1.11
     mixer
    1.09
     mixtures
    1.09
    Activations Density 0.087%

    No Known Activations