© 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. 14681
    Prev
    Next
    INDEX
    Explanations

    the presence of specific markers indicating the beginning of a new section or topic within the document

    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
     iſt
    -1.11
    \<^
    -1.08
     itſelf
    -1.05
     Houſe
    -1.03
     bezeichneter
    -0.98
     houſe
    -0.97
    存于互联网档案馆
    -0.97
     ་་
    -0.97
    NUMX
    -0.94
     Monfieur
    -0.94
    POSITIVE LOGITS
    <bos>
    0.90
    ,
    0.89
    .
    0.88
    ↵
    0.78
     
    0.76
     ,
    0.76
    b
    0.75
    in
    0.74
    ?
    0.74
     s
    0.73
    Activations Density 1.032%

    No Known Activations