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. 15-GEMMASCOPE-RES-16K
    6. 8986
    Prev
    Next
    INDEX
    Explanations

    mentions of specific single musical tracks or albums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pautan
    -0.55
    ConverterFactory
    -0.48
    يميديا
    -0.48
    IInterface
    -0.47
     أعلام
    -0.44
     safety
    -0.43
    外部連結
    -0.42
     sih
    -0.42
    quién
    -0.40
     hourly
    -0.40
    POSITIVE LOGITS
     now
    1.56
     Now
    1.37
    now
    1.29
    Now
    1.26
     today
    1.25
     ahora
    1.17
     ngayon
    1.14
     maintenant
    1.13
     Today
    1.13
     aujourd
    1.10
    Activations Density 0.485%

    No Known Activations