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. 24-GEMMASCOPE-RES-16K
    6. 12690
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various contexts and forms

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

    Follows "be" and indicates a future action

    np_acts-logits-general · gemini-2.0-flash

    be + future or ongoing action/state

    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
     egentlig
    -0.64
     currently
    -0.60
    已經
    -0.55
    currently
    -0.55
     already
    -0.54
     Currently
    -0.53
     MainAxisSize
    -0.53
     actually
    -0.52
    Originally
    -0.52
     tartalomajánló
    -0.52
    POSITIVE LOGITS
     prochain
    0.94
     soon
    0.86
     tomorrow
    0.84
     forever
    0.77
     bientôt
    0.77
    tomorrow
    0.74
    SharedCtor
    0.74
     needing
    0.72
    soon
    0.72
    Soon
    0.71
    Activations Density 0.207%

    No Known Activations