© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 634
    Prev
    Next
    INDEX
    Explanations

    references to combinations or blends of different substances or elements

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

    "mixture" or similar words follow

    np_acts-logits-general · gemini-2.0-flash

    mixture of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     MainAxisSize
    -0.59
    nanoTime
    -0.59
    Dermott
    -0.57
    Facades
    -0.56
    urlopen
    -0.56
    noopener
    -0.54
    defineProperty
    -0.53
     PrintWriter
    -0.52
    WebElementEntity
    -0.52
     tận
    -0.50
    POSITIVE LOGITS
     mix
    1.45
     Mix
    1.27
     MIX
    1.24
    mix
    1.23
     mixture
    1.22
    Mix
    1.20
     mixes
    1.18
     mixtures
    1.17
     mixing
    1.14
    MIX
    1.13
    Activations Density 0.128%

    No Known Activations