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. 8236
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prior completion or ongoing status

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

    Follows the word "already."

    np_acts-logits-general · gemini-2.0-flash

    already happened or known

    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
    still
    -1.28
     still
    -1.27
     todavía
    -1.16
     fortfarande
    -1.11
     هنوز
    -1.09
     aún
    -1.08
    Still
    -1.07
     ancora
    -1.06
     Still
    -1.06
     ainda
    -1.06
    POSITIVE LOGITS
     begun
    0.84
     established
    0.80
     underway
    0.72
     halfway
    0.71
    established
    0.65
     exists
    0.65
     proven
    0.65
     existed
    0.62
     existant
    0.60
     existing
    0.59
    Activations Density 0.106%

    No Known Activations