© 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. 20-GEMMASCOPE-RES-16K
    11. 7264
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical or formal logic terms and control structures in the text

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

    Code or markup fragments

    np_acts-logits-general · gemini-2.0-flash

    DestName or >C states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BENEF
    -0.51
    IRQn
    -0.50
    =$_
    -0.50
    FormTagHelper
    -0.50
    hasMoreElements
    -0.49
     发表于
    -0.49
     resourceCulture
    -0.48
     Factbook
    -0.47
    DebuggerNonUser
    -0.47
    PathParam
    -0.47
    POSITIVE LOGITS
     Chwiliwch
    0.73
     الرياضيه
    0.66
    makeText
    0.58
    saraba
    0.58
     ModelExpression
    0.58
     olyan
    0.57
     سكانية
    0.57
     nyelven
    0.57
    해서
    0.56
    closeConnection
    0.56
    Activations Density 0.165%

    No Known Activations