© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or financial issues, particularly involving taxes and liens

    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
     uitges
    -0.44
    UrlResolution
    -0.42
     épaules
    -0.42
    verifyException
    -0.41
    botten
    -0.40
     Schluss
    -0.40
    новништво
    -0.40
    世間
    -0.40
    pushFollow
    -0.39
     pollici
    -0.39
    POSITIVE LOGITS
     confirmed
    1.07
     confirm
    0.99
     confirmation
    0.93
     declined
    0.92
     confirms
    0.91
     confirming
    0.91
     confirme
    0.90
     confirmó
    0.90
    confirmed
    0.86
     Confirm
    0.85
    Activations Density 0.201%

    No Known Activations