© 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. 2-GEMMASCOPE-RES-16K
    11. 1371
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to subsets and ideal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.72
     <=",
    -0.62
    GEBURTSDATUM
    -0.60
    例句
    -0.60
    mobileqq
    -0.56
    offsetof
    -0.56
    Erstellt
    -0.54
     onPostExecute
    -0.52
    áctenos
    -0.51
     Abschied
    -0.50
    POSITIVE LOGITS
     faſt
    0.70
    ="#"><
    0.64
     Jefus
    0.60
    Билгалдахарш
    0.60
     MainAxisSize
    0.59
    MLLoader
    0.59
     Winaray
    0.57
     autorytatywna
    0.56
    SupportActionBar
    0.56
     sezione
    0.55
    Activations Density 0.178%

    No Known Activations