© 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. 11011
    Prev
    Next
    INDEX
    Explanations

    document structure indicators such as section headings or formatting cues

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

    Follows less-common initial capitalization

    np_acts-logits-general · gemini-2.0-flash

    combining text and code

    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
    发表于
    -0.52
     بيها
    -0.51
     />\
    -0.50
    .*")]
    -0.50
     שוליים
    -0.50
    хіво
    -0.48
     Нам
    -0.46
     لينك
    -0.45
    iestety
    -0.43
    ześnie
    -0.42
    POSITIVE LOGITS
    LookAnd
    0.79
    Personensuche
    0.70
    Suara
    0.68
    ThroughAttribute
    0.66
    unmodifiable
    0.66
     BioLib
    0.65
    WriteTagHelper
    0.64
    UnsafeEnabled
    0.63
     tarko
    0.62
     myö
    0.59
    Activations Density 0.100%

    No Known Activations