© 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. 3-GEMMASCOPE-RES-16K
    11. 9385
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests, obligations, or the need for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mişti
    -0.69
    miyorum
    -0.63
    AccessorTable
    -0.48
    siąż
    -0.47
     fallu
    -0.47
    GCS
    -0.47
    diğim
    -0.44
    raf
    -0.43
    FORMA
    -0.43
    Становништво
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.89
    enterOuterAlt
    0.72
     TimeUnit
    0.71
     Offisielt
    0.68
    VersionUID
    0.68
    mentable
    0.68
    TimeUnit
    0.65
    ValueStyle
    0.64
     المعيارى
    0.62
    #+#
    0.61
    Activations Density 0.159%

    No Known Activations