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. 2-GEMMASCOPE-RES-16K
    6. 15224
    Prev
    Next
    INDEX
    Explanations

    phrases and actions that indicate making a point or highlighting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    NewReader
    -0.59
     Either
    -0.58
    ranging
    -0.53
     оригіналу
    -0.53
    Either
    -0.53
    !("{}",
    -0.51
    pede
    -0.50
     gir
    -0.50
    ariales
    -0.49
    tiges
    -0.49
    POSITIVE LOGITS
     souligné
    0.84
     señalar
    0.79
     segnal
    0.77
     pointed
    0.76
     remarquer
    0.75
     remarqué
    0.75
     noted
    0.74
     noticed
    0.74
     soulign
    0.72
     отметить
    0.71
    Activations Density 0.357%

    No Known Activations