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. 4-GEMMASCOPE-RES-16K
    6. 3585
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically related to the present and recent past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.71
    PYX
    -0.68
    ########.
    -0.67
    pkins
    -0.67
     يتيمه
    -0.66
     LIABLE
    -0.64
     بيها
    -0.62
    Obras
    -0.62
    ConstraintMaker
    -0.61
     Serrano
    -0.60
    POSITIVE LOGITS
     this
    0.81
    istisches
    0.62
     THIS
    0.61
     acestui
    0.57
     côtes
    0.56
     nyky
    0.55
     até
    0.54
     întâ
    0.54
    Màu
    0.53
    IMPORTED
    0.53
    Activations Density 0.126%

    No Known Activations