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. 25-GEMMASCOPE-RES-16K
    6. 5029
    Prev
    Next
    INDEX
    Explanations

    sequences of characters and numbers, particularly in a technical or code-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.57
    ogenes
    -0.49
     усе
    -0.48
     Nether
    -0.47
    fjspx
    -0.45
    endregion
    -0.45
     Audiodateien
    -0.45
    aarrggbb
    -0.45
     <",
    -0.44
     Shakspeare
    -0.43
    POSITIVE LOGITS
     ")[
    0.63
    InjectAttribute
    0.61
     ')[
    0.61
    انيف
    0.57
     grecque
    0.55
     citoyen
    0.55
    Pyx
    0.55
     незавершена
    0.53
     actuel
    0.50
    ніципа
    0.50
    Activations Density 0.460%

    No Known Activations