© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10616
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or list components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.63
     another
    -0.62
     cà
    -0.60
     مشين
    -0.59
    تاريخ
    -0.59
     Jefus
    -0.58
     Conſ
    -0.58
     Diſ
    -0.57
     ſen
    -0.56
    Ύ
    -0.56
    POSITIVE LOGITS
     including
    0.88
    voorbeeld
    0.87
    INCLUDING
    0.86
     zoals
    0.86
     like
    0.86
    including
    0.82
     telles
    0.82
     např
    0.81
    Including
    0.79
     INCLUDING
    0.77
    Activations Density 0.152%

    No Known Activations