© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1765
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to equations or inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entie
    -0.50
     Smart
    -0.46
    ാൻ
    -0.45
    ARIS
    -0.45
    bitField
    -0.45
    daction
    -0.43
    Lähteet
    -0.43
    Kap
    -0.42
    ására
    -0.42
     ['
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    0.93
     BoxDecoration
    0.87
     pinulongan
    0.81
     propOrder
    0.79
     QtWidgets
    0.79
     PhpStorm
    0.78
     Chwiliwch
    0.76
    AlterField
    0.73
     оригіналу
    0.72
    \{\\
    0.72
    Activations Density 0.572%

    No Known Activations