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. 1-GEMMASCOPE-RES-16K
    6. 6135
    Prev
    Next
    INDEX
    Explanations

    terms related to lifting or elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stiller
    -0.57
     fireplace
    -0.55
    PackageInfo
    -0.53
     sympathique
    -0.52
    ਆਂ
    -0.52
    haway
    -0.51
    uera
    -0.50
     červená
    -0.50
     considération
    -0.50
    sipasi
    -0.50
    POSITIVE LOGITS
     Lift
    1.08
     lift
    1.05
     lifts
    0.95
     Today
    0.93
    TODAY
    0.92
    Lift
    0.90
    Today
    0.89
     LIFT
    0.83
     trên
    0.82
    lift
    0.81
    Activations Density 0.101%

    No Known Activations