© 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. 8-GEMMASCOPE-RES-16K
    6. 6944
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of attention or focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whitehead
    -0.61
    raborty
    -0.60
     Gefühle
    -0.60
    bootstrapcdn
    -0.59
     maestra
    -0.59
    QUADS
    -0.59
    iegler
    -0.58
    ://
    -0.58
     profeta
    -0.58
     nemici
    -0.58
    POSITIVE LOGITS
     attention
    2.32
     Attention
    2.12
    attention
    1.95
     ATTENTION
    1.94
    Attention
    1.89
     attentions
    1.73
    ATTENTION
    1.66
     Atención
    1.36
     aten
    1.32
    attenzione
    1.32
    Activations Density 0.048%

    No Known Activations