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. 10968
    Prev
    Next
    INDEX
    Explanations

    expressions indicating time or temporal relationships

    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
    IVEREF
    -0.81
    CppMethod
    -0.80
     utafitiHapana
    -0.79
    PMailer
    -0.77
    AddTagHelper
    -0.77
    parsedMessage
    -0.76
    原始内容存档于
    -0.75
     Normdatei
    -0.73
    Obrázky
    -0.73
    DeleteMapping
    -0.71
    POSITIVE LOGITS
     because
    0.54
    หมด
    0.53
    .
    0.50
     if
    0.46
    ArgumentParser
    0.45
    startswith
    0.45
     Keuangan
    0.44
     anymore
    0.43
    ्म
    0.43
    ########.
    0.43
    Activations Density 0.556%

    No Known Activations