© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9078
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to camera lenses and optical performance

    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
     competitivos
    -0.34
     Fore
    -0.29
    震惊
    -0.29
    arakat
    -0.28
    NameInMap
    -0.27
     alive
    -0.27
    有名
    -0.27
     raising
    -0.26
    raise
    -0.26
     en
    -0.26
    POSITIVE LOGITS
    AddTagHelper
    0.78
     transfieras
    0.71
     lenses
    0.68
     AssemblyCompany
    0.67
    featureID
    0.66
    rrggbb
    0.66
     telescopes
    0.63
     binoculars
    0.59
     lens
    0.59
     AssemblyCulture
    0.59
    Activations Density 0.286%

    No Known Activations