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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8244
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibilities, options, or necessary actions

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

    Following "one" plus a modal verb

    np_acts-logits-general · gemini-2.0-flash

    one can/may/might

    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
     autorytatywna
    -0.66
     AssemblyCulture
    -0.57
    arrête
    -0.53
    dhury
    -0.51
    áře
    -0.51
    MessageTagHelper
    -0.49
     Agr
    -0.49
     spodnie
    -0.49
     ویکی‌پدی
    -0.48
    __":
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.89
     cannot
    0.70
    expects
    0.69
     can
    0.68
     expects
    0.63
     could
    0.62
     oneself
    0.60
    eseorang
    0.58
     might
    0.57
     gelangt
    0.56
    Activations Density 0.085%

    No Known Activations