© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    reported actions and findings in various contexts

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

    scientific reporting verbs like "reported", "found", "stated", and "showed".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    past-tense verbs, especially reporting or action verbs indicating completed events.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    past tense verbs in formal or academic writing, particularly those reporting research findings or actions taken.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
     pleaſure
    -0.68
     houſe
    -0.61
     ſtate
    -0.61
     Houſe
    -0.56
     ſche
    -0.52
    ſelf
    -0.50
     ſtre
    -0.49
    Lycka
    -0.48
    ChildScrollView
    -0.46
    Consigli
    -0.46
    POSITIVE LOGITS
    ized
    0.71
    iked
    0.71
    ched
    0.67
    ened
    0.67
    igned
    0.66
    ted
    0.66
     propOrder
    0.66
    unked
    0.66
    ked
    0.65
    pped
    0.64
    Activations Density 0.846%

    No Known Activations