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. 21-GEMMASCOPE-RES-16K
    6. 8276
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structural formatting within mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.62
    InitVars
    -0.61
    antd
    -0.59
     HttpNotFound
    -0.58
    DockStyle
    -0.58
    Gön
    -0.58
    cartier
    -0.57
    protoimpl
    -0.56
    featureID
    -0.55
     Thoreau
    -0.55
    POSITIVE LOGITS
     xmlns
    0.79
    math
    0.76
     display
    0.73
    MathML
    0.61
    发表于
    0.55
    semantics
    0.55
    țional
    0.54
    }();
    0.52
     Display
    0.51
    oudoune
    0.50
    Activations Density 0.180%

    No Known Activations