© 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. 5-GEMMASCOPE-RES-16K
    11. 987
    Prev
    Next
    INDEX
    Explanations

    instances of assertions or claims being made and their reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    -0.78
     po
    -0.76
    w
    -0.76
    老
    -0.75
     ma
    -0.74
     ge
    -0.71
     lot
    -0.71
    g
    -0.71
    s
    -0.70
     e
    -0.68
    POSITIVE LOGITS
     myſelf
    1.46
     itſelf
    1.33
     purpoſe
    1.30
     pleaſure
    1.22
     Monfieur
    1.21
    ſelf
    1.21
     reaſon
    1.21
     themſelves
    1.17
     obſ
    1.17
     '\\;'
    1.17
    Activations Density 0.134%

    No Known Activations