© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1356
    Prev
    Next
    INDEX
    Explanations

    specific information related to local government and council activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    past events and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Jefus
    -0.68
    alakip
    -0.66
     Wikiseite
    -0.66
     indígen
    -0.64
    rungsseite
    -0.63
    pecabe
    -0.61
     Monfieur
    -0.61
     functionalities
    -0.61
    brinco
    -0.61
     purpoſe
    -0.60
    POSITIVE LOGITS
     was
    0.43
    當時
    0.42
    当时
    0.42
     Later
    0.41
     later
    0.39
    当时的
    0.37
     ['$
    0.36
    IsPostBack
    0.35
    eqn
    0.35
    barten
    0.35
    Activations Density 0.133%

    No Known Activations