© 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. 36-GEMMASCOPE-RES-16K
    11. 11694
    Prev
    Next
    INDEX
    Explanations

    terms related to purity or ideal states in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.40
     بابا
    -0.36
    ANTLR
    -0.35
     चीज़ों
    -0.34
     ويكيپيديا
    -0.33
    toHaveBeen
    -0.32
    khov
    -0.32
    OffsetX
    -0.32
     allAfrica
    -0.32
    pickle
    -0.31
    POSITIVE LOGITS
     pure
    3.31
    pure
    2.98
    Pure
    2.73
     Pure
    2.73
     PURE
    2.61
    PURE
    2.42
    纯
    2.34
     purest
    2.31
    純
    2.30
     puro
    2.14
    Activations Density 0.803%

    No Known Activations