© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13420
    Prev
    Next
    INDEX
    Explanations

    the use of the phrase "you know" and variations of it, indicating conversational engagement and acknowledgment

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

    Followed by "know"

    np_acts-logits-general · gemini-2.0-flash

    you know that

    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
    +#+#
    -0.80
    tonode
    -0.70
    MessageOf
    -0.65
     оригіналу
    -0.64
    󠁴
    -0.62
     Autorizaciones
    -0.60
    MarshalTo
    -0.60
    IntoConstraints
    -0.59
     surla
    -0.58
    tagHelperRunner
    -0.57
    POSITIVE LOGITS
    WriteTagHelper
    0.36
    具合
    0.34
     obvious
    0.32
     Sache
    0.31
     Situ
    0.30
     Situation
    0.30
     démocratie
    0.30
    __*/
    0.30
     visibly
    0.29
     fare
    0.29
    Activations Density 0.043%

    No Known Activations