© 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. 20-GEMMASCOPE-RES-16K
    11. 8563
    Prev
    Next
    INDEX
    Explanations

    language related to personal responsibility and accountability

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

    Prepositions indicating a condition or circumstance

    np_acts-logits-general · gemini-2.0-flash

    on X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.70
    ModelSerializer
    -0.65
    */;
    -0.61
    Jereo
    -0.60
     ambienti
    -0.58
    enumii
    -0.58
    Swal
    -0.56
    спеди
    -0.55
    ModelForm
    -0.53
     recensement
    -0.51
    POSITIVE LOGITS
     behalf
    1.44
     basis
    1.12
     occasion
    1.08
     occasions
    1.04
    basis
    0.80
     grounds
    0.79
     ועל
    0.78
     fronts
    0.76
     whim
    0.72
     occas
    0.71
    Activations Density 0.457%

    No Known Activations