© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2124
    Prev
    Next
    INDEX
    Explanations

    references to sports events and participants in competitive settings

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

    following prepositions or subordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    specific phrases following common words

    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
     Moyen
    -0.52
     Paper
    -0.50
    Portály
    -0.48
    SharedCtor
    -0.48
    tacts
    -0.48
    fromnode
    -0.48
    meable
    -0.47
    paper
    -0.46
    น์
    -0.46
    Paper
    -0.46
    POSITIVE LOGITS
     missed
    0.63
     Tiger
    0.60
     Reti
    0.58
    Tiger
    0.56
     Missed
    0.56
    GraphicsUnit
    0.56
    protoimpl
    0.53
     Masters
    0.53
     világ
    0.52
     compatri
    0.51
    Activations Density 0.060%

    No Known Activations