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. 18-GEMMASCOPE-RES-16K
    6. 3774
    Prev
    Next
    INDEX
    Explanations

    references to scientific research and funding initiatives

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

    Sentences ending with periods

    np_acts-logits-general · gemini-2.0-flash

    start of sentences or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.61
    apparently
    -0.61
    Someone
    -0.58
     Somehow
    -0.58
     pinulongan
    -0.56
     apparently
    -0.56
    possibly
    -0.55
    Somehow
    -0.54
    presumably
    -0.54
     Someone
    -0.54
    POSITIVE LOGITS
     Through
    0.85
    Through
    0.84
    今後も
    0.74
     Recently
    0.73
     initiatives
    0.73
     partnerships
    0.72
    これからも
    0.71
     recently
    0.70
    Recently
    0.70
    Launched
    0.68
    Activations Density 0.239%

    No Known Activations