© 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. 33-GEMMASCOPE-RES-16K
    11. 1062
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to electrical and statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.62
    ambién
    -0.54
    AllowAnonymous
    -0.45
     BoxFit
    -0.42
     nhàng
    -0.41
    淋
    -0.41
    styleUrls
    -0.40
     MainAxisSize
    -0.39
    oredCriteria
    -0.39
     estreia
    -0.38
    POSITIVE LOGITS
     whose
    1.86
    whose
    1.65
     Whose
    1.43
     whofe
    1.42
    Whose
    1.38
     whoſe
    1.26
     cuyo
    1.25
     cuya
    1.20
     cujo
    1.13
     cuyas
    1.12
    Activations Density 1.328%

    No Known Activations