© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9534
    Prev
    Next
    INDEX
    Explanations

    specific identifiers, codes, or tags related to video content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    S
    -0.95
    E
    -0.95
    T
    -0.84
    I
    -0.83
    R
    -0.80
    o
    -0.80
    A
    -0.72
    O
    -0.70
    ECTION
    -0.70
    IntoConstraints
    -0.68
    POSITIVE LOGITS
     Roskov
    0.78
    허
    0.60
    يكب
    0.59
    neté
    0.54
     vulgares
    0.53
     supérieures
    0.53
    wäh
    0.50
    Geplaatst
    0.50
    supra
    0.49
     définiti
    0.49
    Activations Density 0.520%

    No Known Activations