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. 3-GEMMASCOPE-RES-16K
    6. 12066
    Prev
    Next
    INDEX
    Explanations

    terms related to the arrival of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Петер
    -0.68
     déb
    -0.62
    ++)
    -0.61
    mathsf
    -0.60
    getString
    -0.60
    BoxShadow
    -0.60
     />}
    -0.60
     इसका
    -0.59
     defecto
    -0.59
     Kitts
    -0.58
    POSITIVE LOGITS
     arrive
    2.96
     arrived
    2.89
     arrival
    2.85
     arrives
    2.82
    arrived
    2.75
     arriving
    2.72
     Arrive
    2.61
     Arrival
    2.58
     arrivals
    2.58
    arrive
    2.51
    Activations Density 0.041%

    No Known Activations