© 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. 8-GEMMASCOPE-RES-16K
    11. 5738
    Prev
    Next
    INDEX
    Explanations

    structural elements of written content or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.65
     Inſ
    -0.62
     fufficient
    -0.61
     Conſ
    -0.59
     Chriftian
    -0.58
     ſte
    -0.58
     fometimes
    -0.58
     houſe
    -0.58
     Reſ
    -0.57
     policiales
    -0.57
    POSITIVE LOGITS
     rowspan
    1.04
    DoubleQuotes
    0.98
    +#+#
    0.80
    principalTable
    0.79
     كومونز
    0.76
    ParallelGroup
    0.75
     defaultstate
    0.74
    multirow
    0.70
    tagHelperRunner
    0.69
    BeginContext
    0.68
    Activations Density 0.018%

    No Known Activations