© 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. 11-GEMMASCOPE-RES-16K
    11. 7349
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific and medical contexts, particularly focusing on materials, interactions, and biochemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transport
    -0.40
     Transport
    -0.36
    ELESS
    -0.34
    onsor
    -0.32
    access
    -0.32
    sizePolicy
    -0.31
     Bür
    -0.31
     to
    -0.30
     TRANSPORT
    -0.30
    principle
    -0.30
    POSITIVE LOGITS
     otomatig
    0.73
     feroit
    0.60
    ſelves
    0.60
     uſ
    0.57
    SPATH
    0.57
     ſever
    0.56
     diſt
    0.56
     GenerationType
    0.55
     ſind
    0.54
    PYX
    0.54
    Activations Density 12.156%

    No Known Activations