Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14654
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to functions, combinations, and properties of convexity and linearity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BlockPos
    -0.57
     ElementRef
    -0.57
     UIApplication
    -0.56
    urten
    -0.56
    RefNanny
    -0.55
     Waray
    -0.55
    最快更新
    -0.54
     &___
    -0.54
    XmlIgnore
    -0.53
    rehension
    -0.53
    POSITIVE LOGITS
     fraction
    0.75
     fractions
    0.69
    Fraction
    0.67
     Fraction
    0.64
     Fractions
    0.64
    protoimpl
    0.60
     percentages
    0.58
     percentage
    0.58
     fractional
    0.56
     weighted
    0.56
    Activations Density 1.126%

    No Known Activations