© 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. 34-GEMMASCOPE-RES-16K
    11. 596
    Prev
    Next
    INDEX
    Explanations

    terms related to covert operations and political intervention by intelligence agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.50
    ########.
    -0.48
     cocaína
    -0.45
     AIDS
    -0.45
    Datuak
    -0.44
     biß
    -0.44
     OMITTED
    -0.43
    ̈́
    -0.42
     cocaine
    -0.41
    landaise
    -0.41
    POSITIVE LOGITS
     Eisenhower
    0.59
     Khrushchev
    0.53
     Korean
    0.53
     Sputnik
    0.49
    Korean
    0.49
    AnchorStyles
    0.49
     Atomic
    0.49
     tubeless
    0.48
     fifties
    0.48
     mambo
    0.46
    Activations Density 0.832%

    No Known Activations