© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2468
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "so" in various contexts

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

    "so" preceding another word

    np_acts-logits-general · gemini-2.0-flash

    so-called phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.65
    ="#"><
    -0.60
    more
    -0.57
    s
    -0.56
    uate
    -0.55
    indépendance
    -0.53
     للمعارف
    -0.52
    MORE
    -0.51
    fold
    -0.50
    noon
    -0.49
    POSITIVE LOGITS
     GenerationType
    0.80
    jour
    0.79
    called
    0.78
    ckeye
    0.78
     called
    0.74
    othed
    0.70
    lider
    0.67
     propOrder
    0.66
     much
    0.65
    oty
    0.64
    Activations Density 0.067%

    No Known Activations