© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 640
    Prev
    Next
    INDEX
    Explanations

    conditional statements or hypothetical scenarios

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

    Following the word "would"

    np_acts-logits-general · gemini-2.0-flash

    hypothetical or conditional phrases with would

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    (=)
    -0.41
    espejo
    -0.39
    ("."
    -0.39
    Eure
    -0.37
     TikTok
    -0.34
     vicenda
    -0.34
     proteção
    -0.34
    (__
    -0.33
     noire
    -0.32
    Hentet
    -0.32
    POSITIVE LOGITS
     would
    1.21
    Would
    1.21
    would
    1.21
     Would
    1.20
     WOULD
    1.13
    OGND
    0.86
     will
    0.83
    ould
    0.81
    ULD
    0.79
     würde
    0.77
    Activations Density 0.163%

    No Known Activations