© 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. 41-GEMMASCOPE-RES-16K
    11. 9432
    Prev
    Next
    INDEX
    Explanations

    specific coding language identifiers and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    竟然
    -0.47
     Pols
    -0.44
    basicConfig
    -0.44
     Trusts
    -0.43
     Hawkins
    -0.42
     lagoons
    -0.42
    VYMaps
    -0.41
    AddTagHelper
    -0.40
    psons
    -0.40
     للمعارف
    -0.40
    POSITIVE LOGITS
    anes
    0.89
    ates
    0.79
    utes
    0.77
    ines
    0.76
    stes
    0.76
     Hines
    0.76
    ales
    0.75
    otes
    0.75
    iles
    0.74
    zes
    0.74
    Activations Density 1.335%

    No Known Activations