© 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. 5805
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface controls and their states

    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
    <eos>
    -0.67
    …
    -0.66
    </em>
    -0.62
     poil
    -0.60
     Big
    -0.57
    oter
    -0.57
    ora
    -0.56
    n
    -0.55
    par
    -0.54
    𝐳
    -0.54
    POSITIVE LOGITS
    Checked
    1.33
    checked
    1.31
     Checked
    1.10
    setChecked
    1.05
    InputBorder
    1.00
    CHECKED
    1.00
    isChecked
    0.97
     незавершена
    0.95
    PerformLayout
    0.92
     myſelf
    0.91
    Activations Density 0.055%

    No Known Activations