© 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 EvalsExportsAPI 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. 12829
    Prev
    Next
    INDEX
    Explanations

    references to governmental or bureaucratic processes

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

    German/Danish-related text

    np_acts-logits-general · gemini-2.0-flash

    historical german optants

    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
     impactful
    -0.87
    Mhm
    -0.86
     incentiv
    -0.84
     showcasing
    -0.84
     itſelf
    -0.83
     myſelf
    -0.83
     transitioning
    -0.83
     showcased
    -0.80
    klart
    -0.79
     transitioned
    -0.77
    POSITIVE LOGITS
     daß
    0.66
     muß
    0.63
     doubtless
    0.58
     skall
    0.58
     läßt
    0.55
     mußte
    0.53
    @[+][
    0.52
    textAppearance
    0.52
    ですから
    0.52
    faßt
    0.51
    Activations Density 0.546%

    No Known Activations