© 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. 10270
    Prev
    Next
    INDEX
    Explanations

    code related to creation and initialization of objects or resources

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

    Code that creates something

    np_acts-logits-general · gemini-2.0-flash

    create or update

    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
     adanya
    -0.44
     recientemente
    -0.43
     haberse
    -0.41
     brindar
    -0.41
    inerja
    -0.41
    ConfigureAwait
    -0.40
     conductas
    -0.40
     tidigare
    -0.40
     quien
    -0.39
     changements
    -0.39
    POSITIVE LOGITS
     empty
    0.73
     new
    0.71
     dummy
    0.69
     Empty
    0.67
     blank
    0.62
    新的
    0.60
    Empty
    0.59
    empty
    0.59
    空的
    0.57
    NewRow
    0.56
    Activations Density 0.439%

    No Known Activations