© 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. 1-GEMMASCOPE-RES-16K
    11. 13871
    Prev
    Next
    INDEX
    Explanations

    references to government or institutional organizations, particularly related to data or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.67
    tempted
    -0.63
    paign
    -0.61
     chi̍t
    -0.54
     slowest
    -0.54
    Rhestr
    -0.53
     fastest
    -0.53
    viewDidLoad
    -0.53
    出版年
    -0.53
    hyrchwyd
    -0.52
    POSITIVE LOGITS
    GOTREF
    0.66
     BUREAU
    0.65
     Bureau
    0.63
    EndContext
    0.62
    SizeF
    0.59
    transQ
    0.59
    una
    0.57
    bor
    0.57
    Alike
    0.55
    enda
    0.54
    Activations Density 2.232%

    No Known Activations