© 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. 2-GEMMASCOPE-RES-16K
    11. 4605
    Prev
    Next
    INDEX
    Explanations

    references to conditions, actions, or contexts specified by the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trải
    -0.48
    ocally
    -0.46
     basically
    -0.45
    众
    -0.44
     trầm
    -0.42
     looking
    -0.41
     key
    -0.41
    ivant
    -0.41
    เร
    -0.41
     erstmal
    -0.40
    POSITIVE LOGITS
    AndEndTag
    1.04
    AddTagHelper
    0.97
     SafeMath
    0.90
    RectangleBorder
    0.89
     محفوظة
    0.86
    EndInit
    0.86
     AssemblyCulture
    0.85
     ProtoMessage
    0.84
    DockStyle
    0.84
    findpost
    0.83
    Activations Density 0.248%

    No Known Activations