© 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. 30-GEMMASCOPE-RES-16K
    11. 12441
    Prev
    Next
    INDEX
    Explanations

    keywords related to data structures or programming concepts

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

    ending in "ed" or "ing" implying a state

    np_acts-logits-general · gemini-2.0-flash

    prepared verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.82
     houſe
    -0.79
     Houſe
    -0.67
     surla
    -0.63
     ſche
    -0.62
     leſs
    -0.62
     ſtate
    -0.61
     reaſon
    -0.61
    ſelf
    -0.61
     fevere
    -0.60
    POSITIVE LOGITS
    ded
    0.54
    ness
    0.50
    isContained
    0.49
    irected
    0.47
    s
    0.45
    ted
    0.44
     Used
    0.43
     Bred
    0.43
     Measured
    0.43
    ried
    0.42
    Activations Density 1.725%

    No Known Activations