© 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. 7329
    Prev
    Next
    INDEX
    Explanations

    words and symbols used in technical or programming contexts

    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
    AnchorStyles
    -0.86
    WaitGroup
    -0.76
     pinulongan
    -0.73
     MainAxisSize
    -0.73
     >=",
    -0.69
    //
    -0.69
    DoubleQuotes
    -0.69
    — 
    -0.68
    Bronnen
    -0.66
    /*
    -0.65
    POSITIVE LOGITS
     himſelf
    0.60
     mijne
    0.59
     espagnole
    0.59
     groote
    0.59
     pleaſure
    0.57
     nôtre
    0.57
     muſt
    0.54
     zijne
    0.54
    <bos>
    0.53
     ſche
    0.53
    Activations Density 1.040%

    No Known Activations