© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11911
    Prev
    Next
    INDEX
    Explanations

    the sequence and order of processes or steps in a procedure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.71
     Numerade
    -0.43
     оригіналу
    -0.42
    marle
    -0.39
    featureID
    -0.37
    parsedMessage
    -0.36
    InitVars
    -0.36
    aktery
    -0.36
     برانيه
    -0.35
    astanza
    -0.35
    POSITIVE LOGITS
     sequence
    2.25
     sequential
    1.91
     Sequence
    1.86
    sequence
    1.82
     sequentially
    1.78
    Sequence
    1.75
    顺序
    1.75
     sequencing
    1.73
     sequenced
    1.71
     sequences
    1.66
    Activations Density 1.026%

    No Known Activations