© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    code elements and data structures used in programming contexts

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

    Code-related, especially printing or outputting data

    np_acts-logits-general · gemini-2.0-flash

    code, math, or data delimiters

    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
    IUrlHelper
    -0.81
    SourceChecksum
    -0.78
    __':
    -0.77
    UnusedPrivate
    -0.76
    `{.
    -0.75
    ільки
    -0.75
     createState
    -0.75
     архивлан
    -0.75
    IBOutlet
    -0.74
    ')):
    -0.74
    POSITIVE LOGITS
    toString
    0.59
     vs
    0.56
     ==
    0.50
     could
    0.49
    inspect
    0.49
     versus
    0.48
    ================
    0.46
    是否
    0.45
     verdi
    0.44
     pprint
    0.43
    Activations Density 0.104%

    No Known Activations