© 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. 2-GEMMASCOPE-RES-16K
    11. 14457
    Prev
    Next
    INDEX
    Explanations

    phrases related to proximity and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.46
    army
    -0.45
     parseFrom
    -0.45
     onStart
    -0.44
    Demografía
    -0.41
    XCT
    -0.41
     Protected
    -0.41
    bzero
    -0.41
     irritate
    -0.40
     Normdatei
    -0.40
    POSITIVE LOGITS
     closest
    0.72
     containing
    0.59
     Congress
    0.56
     CONGRESS
    0.52
    containing
    0.51
    closest
    0.48
     nearest
    0.47
    Congress
    0.46
     furthest
    0.46
     representative
    0.44
    Activations Density 0.080%

    No Known Activations