© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    locations and addresses

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

    Location or floor information

    np_acts-logits-general · gemini-2.0-flash

    floors and suites

    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
    Personendaten
    -0.47
    èdia
    -0.37
     propOrder
    -0.34
    PRNewswire
    -0.34
    #+#
    -0.34
     disambiguazione
    -0.34
    autoreleasepool
    -0.34
    oredCriteria
    -0.33
     článku
    -0.32
    glBindBuffer
    -0.31
    POSITIVE LOGITS
     upstairs
    1.45
     downstairs
    1.22
     basement
    1.03
     floor
    1.02
     upper
    1.01
     floors
    0.98
    Upstairs
    0.98
    ชั้น
    0.97
     ground
    0.95
     étage
    0.93
    Activations Density 0.110%

    No Known Activations