© 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. 22-GEMMASCOPE-RES-16K
    11. 4832
    Prev
    Next
    INDEX
    Explanations

    statements that reference principles, conclusions, and their applicability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "apply/applies/applied"

    np_acts-logits-general · gemini-2.0-flash

    principle applies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.63
    /**
    -0.59
    transQ
    -0.57
     يتيمه
    -0.57
    Hentet
    -0.56
    setVerticalGroup
    -0.52
     Dafür
    -0.51
     préf
    -0.50
    IZON
    -0.48
     coû
    -0.48
    POSITIVE LOGITS
     apply
    2.64
     applies
    2.53
     applied
    2.33
    apply
    2.27
     Apply
    2.23
     applying
    2.16
    Apply
    2.10
    applied
    2.07
     Applies
    2.04
     Applying
    2.02
    Activations Density 0.830%

    No Known Activations