© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    character references associated with familial relationships

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

    verb forms of "to be"

    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
    ViewImports
    -0.33
    schlag
    -0.32
     practice
    -0.30
     direct
    -0.29
     rozpo
    -0.29
    SequentialGroup
    -0.28
     pleno
    -0.28
     recognition
    -0.28
    jenigen
    -0.27
     simak
    -0.27
    POSITIVE LOGITS
    ſchen
    0.74
    Personendaten
    0.69
     müſſen
    0.69
     Autorizaciones
    0.68
    ſehen
    0.68
    Personensuche
    0.67
    iſchen
    0.66
    ReusableCell
    0.66
    enablog
    0.65
    JspWriter
    0.65
    Activations Density 0.034%

    No Known Activations