Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 116901
    Prev
    Next
    INDEX
    Explanations

    phrases referring to birth and living status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    born and birthdates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.59
    ighborhood
    -0.57
    ppm
    -0.50
    XtraEditors
    -0.49
     ErrIntOverflow
    -0.48
     désolés
    -0.48
     Administrativna
    -0.48
     poul
    -0.47
     ppm
    -0.47
    lickr
    -0.46
    POSITIVE LOGITS
     born
    0.75
     birth
    0.64
    GEBURTSDATUM
    0.62
    født
    0.61
     doğum
    0.59
    GEBURTS
    0.58
     naissance
    0.58
    birthdate
    0.57
     Born
    0.56
    Born
    0.56
    Activations Density 0.016%

    No Known Activations