Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10141
    Prev
    Next
    INDEX
    Explanations

    the concept of "special" or "specialized" elements or instances

    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
     незавершена
    -1.11
     kaynağından
    -1.08
    OGND
    -0.91
    Portale
    -0.89
    SequentialGroup
    -0.86
    IVEREF
    -0.86
     Akismet
    -0.86
    EndInit
    -0.86
    ERICK
    -0.85
     scythe
    -0.84
    POSITIVE LOGITS
     special
    2.87
     Special
    2.73
    Special
    2.62
    special
    2.52
    SPECIAL
    2.42
     SPECIAL
    2.39
     speciale
    1.94
     especiales
    1.92
     specials
    1.91
     Specials
    1.86
    Activations Density 0.056%

    No Known Activations