© 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. 21-GEMMASCOPE-RES-16K
    11. 12846
    Prev
    Next
    INDEX
    Explanations

    contexts or situations that denote specific stages or points in a discussion or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cív
    -0.46
    AutoModerator
    -0.44
     trainings
    -0.44
    OGND
    -0.44
     imprimible
    -0.42
     gratuits
    -0.41
     Trainings
    -0.38
     volantes
    -0.37
    phosa
    -0.36
    𝟹
    -0.36
    POSITIVE LOGITS
    utilisons
    0.54
     Italijani
    0.53
     waarbij
    0.52
    BuildContext
    0.51
     Здесь
    0.51
    adaptiveStyles
    0.50
    Тут
    0.50
     Тут
    0.49
    INCREF
    0.48
     EconPapers
    0.48
    Activations Density 0.368%

    No Known Activations