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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3309
    Prev
    Next
    INDEX
    Explanations

    quantifiable counts or numbers related to subjects discussed in the text

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

    numbers and quantities that enumerate items or groups.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.56
     lenker
    -0.52
    TemporalType
    -0.50
     milliers
    -0.49
    Hundreds
    -0.49
     transfieras
    -0.48
     centaines
    -0.47
    再來
    -0.47
    stuff
    -0.46
    ьаж
    -0.46
    POSITIVE LOGITS
     different
    0.76
     distinct
    0.65
     separate
    0.63
     kinds
    0.59
     very
    0.56
     instances
    0.54
     pieces
    0.53
    different
    0.52
    zehn
    0.52
     sets
    0.52
    Activations Density 0.717%

    No Known Activations