© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4182
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an urge or motivation to encourage action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RuleContext
    -0.67
    rüstung
    -0.61
    рома
    -0.59
     spect
    -0.58
    Spectrum
    -0.56
     portátil
    -0.55
    qrstuvwxyz
    -0.55
    getOptions
    -0.55
    cerna
    -0.55
     Diana
    -0.55
    POSITIVE LOGITS
     push
    3.67
     Push
    3.24
     pushes
    3.11
     pushed
    3.10
     pushing
    3.07
     PUSH
    3.07
    Push
    2.94
     Pushing
    2.93
    push
    2.90
    Pushing
    2.79
    Activations Density 0.055%

    No Known Activations