© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4394
    Prev
    Next
    INDEX
    Explanations

    structured code elements and data definitions in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.58
     besides
    -0.56
     Besides
    -0.52
    besides
    -0.51
    Besides
    -0.50
    VideoCapture
    -0.50
     concessions
    -0.49
    Bianca
    -0.48
     Alquiler
    -0.46
     Concession
    -0.46
    POSITIVE LOGITS
    afficheront
    0.40
     random
    0.37
     iprot
    0.36
    Lorem
    0.35
     quelque
    0.35
    some
    0.34
     some
    0.34
    nezeu
    0.33
     abc
    0.33
     morire
    0.33
    Activations Density 1.292%

    No Known Activations