© 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. 0-GEMMASCOPE-RES-16K
    11. 8231
    Prev
    Next
    INDEX
    Explanations

    references to HTML and XML attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.45
     Vernunft
    -0.41
     Bühne
    -0.40
     Öffentlichkeit
    -0.40
     Ciencia
    -0.39
    occasione
    -0.37
     Verpflichtung
    -0.37
     Schritt
    -0.37
     Botschaft
    -0.36
     Verantwortung
    -0.36
    POSITIVE LOGITS
     attribute
    1.16
     att
    1.10
     Attribute
    1.05
    attr
    1.03
     attr
    1.03
    att
    0.98
    attribute
    0.96
     Att
    0.94
    Att
    0.91
     attribu
    0.89
    Activations Density 0.250%

    No Known Activations