Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6611
    Prev
    Next
    INDEX
    Explanations

    instances of the word "told" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hervor
    -0.68
    KommentareTeilen
    -0.68
    ValueGenerated
    -0.67
     verschil
    -0.66
     Argyle
    -0.64
     Nachweis
    -0.64
     riconoscimento
    -0.62
     régulière
    -0.62
     bunda
    -0.61
    Демографія
    -0.61
    POSITIVE LOGITS
     told
    2.89
    told
    2.55
     Told
    2.51
    Told
    2.39
     telling
    1.51
     tells
    1.48
    Telling
    1.42
     Tells
    1.35
     tell
    1.35
    telling
    1.30
    Activations Density 0.133%

    No Known Activations