© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1785
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indígen
    -0.71
    pulseira
    -0.65
     desmotivaciones
    -0.59
     increí
    -0.58
     ſont
    -0.57
     myſelf
    -0.56
     saveiro
    -0.55
     Perſ
    -0.55
     mauva
    -0.55
     ainfi
    -0.53
    POSITIVE LOGITS
     Unfortunately
    0.68
     However
    0.67
     CanadaChoose
    0.64
     Finally
    0.62
     Although
    0.61
    ureusement
    0.60
     Especially
    0.60
     Fortunately
    0.59
     Until
    0.59
     Though
    0.58
    Activations Density 0.960%

    No Known Activations