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. 12-GEMMASCOPE-RES-16K
    6. 10165
    Prev
    Next
    INDEX
    Explanations

    mentions of Apple and its products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.79
    ⓧ
    -0.66
    addContainerGap
    -0.64
    UnusedPrivate
    -0.61
    rungsseite
    -0.58
    elemField
    -0.57
    VIAF
    -0.57
    addPreferredGap
    -0.56
    IntentFilter
    -0.56
     Holman
    -0.55
    POSITIVE LOGITS
     Apple
    1.61
    Apple
    1.46
     APPLE
    1.42
     Apples
    1.37
     apple
    1.37
    apple
    1.32
     apples
    1.28
    pertino
    1.23
    Apples
    1.22
    apples
    1.22
    Activations Density 0.191%

    No Known Activations