© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2686
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mix" in various forms and contexts, often related to combinations or mixtures

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

    phrases containing "mix" or "mixed" followed by "of" or a descriptor like "martial arts" or "doubles."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "mixed" or "mix" appearing at the beginning of phrases or clauses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.59
    WebElementEntity
    -0.56
    richTextPanel
    -0.55
    httphttps
    -0.54
    ChromeDriver
    -0.54
    ronpa
    -0.52
    ClientRect
    -0.52
    rinfo
    -0.50
    UrlResolution
    -0.50
    MethodManager
    -0.48
    POSITIVE LOGITS
     mix
    1.24
     Mix
    1.17
     MIX
    1.14
     mixed
    1.11
    Mix
    1.08
     mixing
    1.07
     mixes
    1.04
    MIX
    1.03
    mix
    1.01
     mixer
    1.00
    Activations Density 0.165%

    No Known Activations