© 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. 16-GEMMASCOPE-RES-16K
    6. 14668
    Prev
    Next
    INDEX
    Explanations

    instances of arriving at or reaching a destination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "arrived" or "arrival"

    np_acts-logits-general · gemini-2.0-flash

    verb arrive at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ello
    -0.60
     #
    -0.54
    setString
    -0.54
    </i>
    -0.50
     дописавши
    -0.49
     вопросам
    -0.49
     it
    -0.48
     phận
    -0.48
     Kitts
    -0.48
    فس
    -0.48
    POSITIVE LOGITS
     Arrival
    1.30
     arrives
    1.22
    arrived
    1.22
     arrivals
    1.21
     Arrive
    1.21
     arrival
    1.19
     arrived
    1.17
     arrive
    1.14
    Arri
    1.14
     Arrived
    1.13
    Activations Density 0.063%

    No Known Activations