© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2546
    Prev
    Next
    INDEX
    Explanations

    the concept of consistency and reliable patterns in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.85
     مرئيه
    -0.81
    CppMethod
    -0.74
     للمعارف
    -0.73
    DoubleQuotes
    -0.71
    irited
    -0.69
     يتيمه
    -0.68
    ValueStyle
    -0.64
    írus
    -0.64
    Parcelize
    -0.62
    POSITIVE LOGITS
     consistent
    0.76
     Consistency
    0.74
     throughout
    0.74
     Consistent
    0.73
    consistent
    0.69
    Consistent
    0.67
     inconsistent
    0.66
    Consistency
    0.66
    Uniform
    0.64
     consistency
    0.64
    Activations Density 0.239%

    No Known Activations