© 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. 5-GEMMASCOPE-RES-16K
    11. 5071
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.70
     mergeFrom
    -0.66
    Additionally
    -0.66
     Additionally
    -0.64
     indisponible
    -0.64
     Asimismo
    -0.61
     hereinafter
    -0.60
     additionally
    -0.60
     Normdatei
    -0.57
    IsInitialized
    -0.57
    POSITIVE LOGITS
     montón
    0.65
     maybe
    0.64
     yeah
    0.62
     وتسجيلات
    0.62
    paksa
    0.60
     disambiguazione
    0.60
     Yeah
    0.60
     whatever
    0.60
     Maybe
    0.59
    ❋
    0.59
    Activations Density 0.214%

    No Known Activations