© 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. 11088
    Prev
    Next
    INDEX
    Explanations

    the word "so" and its variations across different contexts

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

    "So" or "SO"

    np_acts-logits-general · gemini-2.0-flash

    so, So, SO

    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
     <<<<<<<<<<<<<<
    -0.90
    SharedCtor
    -0.72
     فريبيس
    -0.71
    ########.
    -0.69
    Bioaccumulative
    -0.67
     Akismet
    -0.66
     AssemblyCulture
    -0.66
    رشف
    -0.66
    saraba
    -0.65
     nahilalakip
    -0.63
    POSITIVE LOGITS
     disant
    0.79
     Socorro
    0.66
     forth
    0.60
    called
    0.59
     much
    0.58
     Sos
    0.57
     BeautifulSoup
    0.55
     isoto
    0.54
    Soto
    0.53
     far
    0.53
    Activations Density 0.269%

    No Known Activations