© 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. 3-GEMMASCOPE-RES-16K
    11. 9285
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of beginning or opening a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.69
    SourceChecksum
    -0.68
     itch
    -0.58
    Activités
    -0.56
    ėms
    -0.56
     matang
    -0.54
    IBOutlet
    -0.53
    Collegamenti
    -0.51
    styleType
    -0.51
     giovane
    -0.51
    POSITIVE LOGITS
     CreateTagHelper
    0.69
    先是
    0.67
     Walkover
    0.66
    startsWith
    0.65
    まず
    0.64
    StartsWith
    0.61
    начала
    0.60
    最初に
    0.59
    先
    0.59
    Firstly
    0.58
    Activations Density 0.167%

    No Known Activations