Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 15243
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "delete" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meanor
    -0.77
    ocks
    -0.74
    atisk
    -0.71
     htons
    -0.70
     ICommand
    -0.70
    CharStream
    -0.65
    jsxFileName
    -0.64
    تيجة
    -0.64
     Roskov
    -0.63
    bkz
    -0.63
    POSITIVE LOGITS
    DeleteMapping
    1.60
     Delete
    1.37
     DELETE
    1.36
     delete
    1.32
    Delete
    1.26
     deletes
    1.25
    DELETE
    1.24
    delete
    1.23
     Deletes
    1.22
     deleting
    1.22
    Activations Density 0.082%

    No Known Activations