© 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 - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3878
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to set theory and calculus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.60
     ligiloj
    -0.58
    Cyfeiriadau
    -0.57
     snippetHide
    -0.56
    httphttps
    -0.54
     enfans
    -0.53
     BoxDecoration
    -0.52
    منابع
    -0.51
    قایناقلار
    -0.50
     povezave
    -0.49
    POSITIVE LOGITS
    leftrightarrow
    0.81
    rightarrow
    0.78
    leftarrow
    0.76
    Leftrightarrow
    0.74
    seteq
    0.72
    Rightarrow
    0.71
    triangleright
    0.65
    otimes
    0.63
    vdash
    0.63
    Longrightarrow
    0.63
    Activations Density 0.935%

    No Known Activations