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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 4219
    Prev
    Next
    INDEX
    Explanations

    questions related to personal preferences and choices

    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
    σουν
    -0.56
    σουμε
    -0.51
     initial
    -0.47
     susi
    -0.46
     appeared
    -0.45
    mişti
    -0.44
    appeared
    -0.44
     داشتند
    -0.43
    ন্
    -0.43
     increase
    -0.42
    POSITIVE LOGITS
     daily
    1.30
     regularly
    1.28
     routinely
    1.14
     everyday
    1.08
     often
    1.07
     frequently
    1.06
    daily
    1.05
     annually
    1.05
     infrequently
    1.04
     yearly
    1.03
    Activations Density 0.480%

    No Known Activations