© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    dialogue and conversational exchanges between characters

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

    questions and polite phrases

    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
     Administrativna
    -0.51
    AddTagHelper
    -0.51
    RegressionTest
    -0.50
    awtextra
    -0.48
    lccn
    -0.47
    MessageOf
    -0.47
    gonic
    -0.44
    enterOuterAlt
    -0.44
    #+#
    -0.42
     anticipates
    -0.42
    POSITIVE LOGITS
     rude
    0.40
    verwijspagina
    0.38
     friendly
    0.38
     unfriendly
    0.37
    rud
    0.36
     Dox
    0.36
     سكانية
    0.36
     whoever
    0.36
     rud
    0.36
     Sirs
    0.35
    Activations Density 0.024%

    No Known Activations