© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that express relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CascadeType
    -0.52
    CppCodeGen
    -0.52
    före
    -0.50
    joba
    -0.47
     erbjud
    -0.47
    뷔
    -0.45
    mesis
    -0.45
     möjlighet
    -0.45
    foglal
    -0.44
     disambiguazione
    -0.44
    POSITIVE LOGITS
     highly
    0.65
     extremely
    0.58
     exceedingly
    0.50
     efficient
    0.50
    highly
    0.48
     CreateTagHelper
    0.47
     trustworthy
    0.47
     abundantly
    0.47
     adaptable
    0.47
     Highly
    0.46
    Activations Density 0.230%

    No Known Activations