© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9100
    Prev
    Next
    INDEX
    Explanations

    instances of the word "edit" and its variations in the context of modifying or managing digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     riuscito
    -0.63
    httphttps
    -0.51
    yarnpkg
    -0.51
     Utiliza
    -0.49
    intellij
    -0.46
    "],
    
    -0.46
     eslint
    -0.46
    ayant
    -0.45
     dating
    -0.45
     bå
    -0.45
    POSITIVE LOGITS
     edit
    1.66
     Edit
    1.47
    edit
    1.44
     edits
    1.25
     editing
    1.22
     editors
    1.20
    Edit
    1.16
    edits
    1.15
     EDIT
    1.14
     Edits
    1.07
    Activations Density 0.157%

    No Known Activations