© 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. 585
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to molecular biology and its effects

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

    thus, therefore, so, 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
    Архівовано
    -0.41
    舺
    -0.40
    yntaxException
    -0.40
    CppMethod
    -0.40
    ///</
    -0.37
    /*
    -0.37
     Raven
    -0.37
     
    -0.36
    伯特
    -0.35
     Hab
    -0.35
    POSITIVE LOGITS
     MainAxisSize
    0.62
     thus
    0.57
     therefore
    0.55
    Therefore
    0.53
     joten
    0.50
     Therefore
    0.50
    Thus
    0.49
    Demikian
    0.49
     więc
    0.49
     demuestra
    0.49
    Activations Density 0.499%

    No Known Activations