© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 566
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation or emphatic expressions

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

    consecutive words signaling inference or conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     myös
    -0.59
     außerdem
    -0.54
     zudem
    -0.52
     також
    -0.51
     также
    -0.47
     ayrıca
    -0.47
    rungsseite
    -0.46
     också
    -0.46
     همچنین
    -0.45
    همچنین
    -0.45
    POSITIVE LOGITS
     therefore
    0.52
    Therefore
    0.47
     donc
    0.47
    所以
    0.45
     hence
    0.44
     so
    0.43
     Therefore
    0.42
    Diweddarwch
    0.41
    therefore
    0.41
     所以
    0.40
    Activations Density 0.038%

    No Known Activations