© 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. 16-GEMMASCOPE-RES-16K
    11. 8412
    Prev
    Next
    INDEX
    Explanations

    assertive statements regarding the possibility or feasibility of actions or ideas

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

    Following "is," "it," or ","

    np_acts-logits-general · gemini-2.0-flash

    yes, certainly, possible, empowering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.78
     незавершена
    -0.74
    تقاوى
    -0.74
     فريبيس
    -0.72
    endphp
    -0.71
     виправивши
    -0.71
    Personensuche
    -0.68
    SharedDtor
    -0.68
     AssemblyTitle
    -0.67
    libft
    -0.66
    POSITIVE LOGITS
     definitely
    0.95
     indeed
    0.95
     inderdaad
    0.95
     effectivement
    0.86
     yes
    0.84
     certainly
    0.79
     efectivamente
    0.73
    Definitely
    0.71
     absolutely
    0.70
    ค่ะ
    0.70
    Activations Density 0.292%

    No Known Activations