© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 10795
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical expressions and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.64
     aDecoder
    -0.53
    +#+#
    -0.52
     betweenstory
    -0.48
    programma
    -0.47
    makeText
    -0.47
    rest
    -0.47
     Inflate
    -0.47
     Outs
    -0.46
    stanz
    -0.46
    POSITIVE LOGITS
    lapsingToolbar
    0.70
    HasBeenSet
    0.68
    AndEndTag
    0.68
    jaer
    0.56
     confronti
    0.55
    stateMutability
    0.54
    haustible
    0.54
    ometrial
    0.52
    UVWXYZ
    0.51
    xions
    0.49
    Activations Density 0.702%

    No Known Activations