© 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. 10-GEMMASCOPE-RES-16K
    11. 12440
    Prev
    Next
    INDEX
    Explanations

    code snippets or elements related to functions or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wußt
    -0.82
    lotz
    -0.82
    tershire
    -0.80
    Datuak
    -0.80
     "<?
    -0.77
     Hame
    -0.75
     Muth
    -0.75
    rsiniz
    -0.74
     McLeod
    -0.74
    ésult
    -0.73
    POSITIVE LOGITS
    [toxicity=0]
    0.94
    s
    0.74
    ↵↵
    0.73
     }}"></
    0.71
    ↵
    0.70
    anyahu
    0.68
    WebVitals
    0.68
    رشف
    0.67
    Hozzáférés
    0.63
    󠁿
    0.62
    Activations Density 0.031%

    No Known Activations