© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    formatted mathematical expressions and notations

    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
     referenties
    -1.04
    rungsseite
    -0.88
     techniczne
    -0.81
    })*/
    -0.75
    lepiej
    -0.74
     normaux
    -0.73
     kasarigan
    -0.73
     vectoriales
    -0.70
     Conway
    -0.69
     eenige
    -0.69
    POSITIVE LOGITS
    ^{\
    0.80
    <sub>
    0.80
     للمعارف
    0.78
    _{\
    0.75
    <sup>
    0.73
    _{{\
    0.71
    ($__
    0.70
    +#+#
    0.68
    BASEPATH
    0.65
    UseVisualStyle
    0.64
    Activations Density 0.110%

    No Known Activations