© 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 EvalsExportsinterp-engineNEWAPI 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. 14047
    Prev
    Next
    INDEX
    Explanations

    evidence of personal experiences and opinions related to products or media

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

    "I heard," "I saw," or "I read."

    np_acts-logits-general · gemini-2.0-flash

    information gathering about what is heard

    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
    帖最后由
    -0.62
    typeorm
    -0.59
    GEBURTSDATUM
    -0.50
     ProtoMessage
    -0.49
    kháu
    -0.49
    MLLoader
    -0.47
    pfung
    -0.46
     kasarigan
    -0.46
     OMITBAD
    -0.46
    LayoutConstraint
    -0.46
    POSITIVE LOGITS
     rumours
    1.14
     heard
    1.14
     rumors
    1.12
    听说
    1.10
     reports
    1.05
     rumour
    1.04
     rumor
    1.02
    据说
    1.02
     rumores
    1.00
     reportedly
    0.99
    Activations Density 0.492%

    No Known Activations