© 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. 10-GEMMASCOPE-RES-16K
    11. 4045
    Prev
    Next
    INDEX
    Explanations

    references to data validation and statistical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.60
     المعيارى
    -0.59
    omiast
    -0.55
    NameInMap
    -0.53
     Dichtung
    -0.50
    UnusedPrivate
    -0.50
     Lightboxes
    -0.49
     vrijwilli
    -0.47
     Dusche
    -0.46
    UIControlState
    -0.45
    POSITIVE LOGITS
    Lähteet
    0.51
    出版年
    0.46
     насељу
    0.46
    verifyException
    0.41
     gyhoeddwyd
    0.38
     nakalista
    0.37
     Italijani
    0.33
    IntoConstraints
    0.33
     mut
    0.32
    ("")]
    0.32
    Activations Density 3.183%

    No Known Activations