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. 19-GEMMASCOPE-RES-16K
    6. 224
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical notation and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conver
    -0.50
     Very
    -0.47
    融
    -0.47
    Sol
    -0.46
    Sin
    -0.44
    Dif
    -0.44
     petto
    -0.44
     szer
    -0.43
     Sin
    -0.43
    sin
    -0.43
    POSITIVE LOGITS
    LookAnd
    0.96
     AspNetCore
    0.92
     lenker
    0.90
    AndEndTag
    0.89
     ModelExpression
    0.87
     quelcon
    0.86
    addContainerGap
    0.83
     vettoriale
    0.79
    Бахар
    0.79
     esternos
    0.77
    Activations Density 3.400%

    No Known Activations