© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-GEMMASCOPE-RES-16K
    11. 1208
    Prev
    Next
    INDEX
    Explanations

    database-related date fields in queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.49
     MenuView
    -0.45
     Botschaft
    -0.37
     iconLine
    -0.37
    eaways
    -0.36
     almohada
    -0.36
     henvisninger
    -0.36
     ciência
    -0.36
    Calle
    -0.35
     <<<<<<<<<<<<<<
    -0.35
    POSITIVE LOGITS
    borderFill
    0.51
    DockStyle
    0.46
    ConstraintMaker
    0.45
    EndDate
    0.45
     endDate
    0.45
    TestBed
    0.44
    makeConstraints
    0.42
    Spesifikasi
    0.41
     bound
    0.41
     sportifs
    0.40
    Activations Density 0.791%

    No Known Activations