© 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. 13943
    Prev
    Next
    INDEX
    Explanations

    phrases related to taxpayer support and government services

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

    phone or telephone

    np_acts-logits-general · gemini-2.0-flash

    telephone communication

    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
    enderror
    -0.50
    addPreferredGap
    -0.38
    IsContent
    -0.38
    Geografi
    -0.35
    webElementXpaths
    -0.34
     Aprend
    -0.33
    vair
    -0.31
     nakalista
    -0.31
    Géographie
    -0.31
    addGap
    -0.31
    POSITIVE LOGITS
     phone
    2.97
     telephone
    2.94
     Phone
    2.61
     Telephone
    2.56
    Phone
    2.50
     telefon
    2.47
    telephone
    2.45
     PHONE
    2.44
    phone
    2.42
    Telephone
    2.42
    Activations Density 0.868%

    No Known Activations