© 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. 14-GEMMASCOPE-RES-16K
    11. 3200
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific syntax or formatting conventions used in programming or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.88
     himſelf
    -0.82
    parsedMessage
    -0.80
     itſelf
    -0.77
    StoryboardSegue
    -0.76
     themſelves
    -0.75
    IsContent
    -0.75
     DBNull
    -0.74
     urmă
    -0.74
    Geplaatst
    -0.74
    POSITIVE LOGITS
     O
    0.48
     sais
    0.47
    enumi
    0.46
     De
    0.46
     ++)
    0.45
     izd
    0.45
     ख
    0.44
     teh
    0.42
    !
    0.42
    de
    0.42
    Activations Density 0.044%

    No Known Activations