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. 18-GEMMASCOPE-RES-16K
    6. 4379
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunication and teleportation concepts

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

    starting with "tele" related to communication or transportation

    np_acts-logits-general · gemini-2.0-flash

    teleportation and telecommunication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.66
    ClientSize
    -0.55
    存于互联网档案馆
    -0.54
     Pixabay
    -0.53
    cshtml
    -0.50
    //-----
    -0.49
     reparti
    -0.48
    Buildable
    -0.48
     Normdatei
    -0.47
     Werbung
    -0.47
    POSITIVE LOGITS
     Tele
    1.29
     tele
    1.25
    Tele
    1.19
     TELE
    1.12
    tele
    1.01
     teleport
    1.00
     Teles
    0.93
     TEL
    0.92
    TELE
    0.92
     télé
    0.88
    Activations Density 0.060%

    No Known Activations