© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9187
    Prev
    Next
    INDEX
    Explanations

    phrases related to covering or concealing

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

    "cover" or "covered"

    np_acts-logits-general · gemini-2.0-flash

    covering or being covered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    GEBURTSDATUM
    -0.47
     Eins
    -0.47
    Portale
    -0.47
    냐
    -0.47
    
    -0.45
    BeginContext
    -0.44
    mael
    -0.43
    */].
    -0.42
    inhardt
    -0.42
    jago
    -0.41
    POSITIVE LOGITS
     cover
    2.09
     coverage
    2.08
     Cover
    2.06
    Cover
    2.05
     COVER
    1.99
     covers
    1.96
     covering
    1.95
     Covering
    1.94
     Coverage
    1.94
    cover
    1.94
    Activations Density 0.107%

    No Known Activations