© 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. 25-GEMMASCOPE-RES-16K
    11. 422
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation within complex equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    χρι
    -0.64
     JADX
    -0.55
    ViewFeatures
    -0.52
    AxisAlignment
    -0.52
    पया
    -0.52
    onomía
    -0.49
     assist
    -0.49
     Leich
    -0.48
    mybatisplus
    -0.47
    
    -0.47
    POSITIVE LOGITS
     المعيارى
    0.58
    PasswordEncoder
    0.57
     createState
    0.56
     الحره
    0.49
    }$)
    0.49
    ⎞
    0.49
    ﾟ)
    0.48
    ））
    0.48
    govina
    0.48
     himo
    0.47
    Activations Density 0.923%

    No Known Activations