© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 15454
    Prev
    Next
    INDEX
    Explanations

    beginning-of-sequence tokens, specifically the <bos> markers indicating the start of new text segments.

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    formal introductory phrases in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -1.11
     myſelf
    -0.94
    NUMX
    -0.94
     XNUMX
    -0.92
    setVerticalGroup
    -0.89
    AutoresizingMask
    -0.86
     iſt
    -0.86
     ModelExpression
    -0.85
    httphttps
    -0.85
     fince
    -0.82
    POSITIVE LOGITS
     a
    0.61
    ,
    0.58
     it
    0.54
     the
    0.53
     aquilo
    0.53
     something
    0.51
    F
    0.50
     F
    0.49
     pember
    0.48
    -
    0.48
    Activations Density 0.546%

    No Known Activations