Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11320
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know" 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 @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -0.46
     utilising
    -0.45
     Ferri
    -0.43
     adverts
    -0.43
     article
    -0.42
     itemId
    -0.42
     Whilst
    -0.42
     Article
    -0.41
     utilised
    -0.41
    itemId
    -0.41
    POSITIVE LOGITS
    Know
    1.71
     Know
    1.63
     know
    1.58
    know
    1.52
    KNOW
    1.49
     KNOW
    1.45
    Knows
    1.43
     Knows
    1.34
    knows
    1.34
     knows
    1.30
    Activations Density 0.155%

    No Known Activations