© 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. 18-GEMMASCOPE-RES-16K
    11. 10912
    Prev
    Next
    INDEX
    Explanations

    pieces of code or functions related to task and error handling in programming

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

    Code block context: "with ... as" statement

    np_acts-logits-general · gemini-2.0-flash

    Python code commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.72
     nahilalakip
    -0.68
    SharedCtor
    -0.67
    DebuggerNonUser
    -0.65
    AndEndTag
    -0.64
    ValueStyle
    -0.64
    gonic
    -0.58
    Datuak
    -0.56
    RSpec
    -0.56
     فريبيس
    -0.54
    POSITIVE LOGITS
     Efq
    0.72
     itſelf
    0.72
     houſe
    0.67
     cauſe
    0.64
     purpoſe
    0.62
     raiſ
    0.62
     Jefus
    0.61
     uſed
    0.61
     ſtate
    0.60
     auffi
    0.60
    Activations Density 0.023%

    No Known Activations