© 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. 9-GEMMASCOPE-RES-16K
    11. 14760
    Prev
    Next
    INDEX
    Explanations

    patterns or sections that involve measurements or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.64
    :
    -0.61
     étrangère
    -0.60
    .
    -0.56
     comunista
    -0.55
     zile
    -0.54
     alimentare
    -0.54
     =
    -0.51
    ないので
    -0.51
     biologique
    -0.51
    POSITIVE LOGITS
     كومونز
    1.14
     للمعارف
    1.10
    UIControlState
    1.06
    TagHelper
    1.05
     Мексичка
    1.02
     Савезне
    0.97
     ujednoznacz
    0.97
    ReusableCell
    0.96
    +#+#
    0.93
    PreferredItem
    0.93
    Activations Density 0.411%

    No Known Activations