© 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. 10964
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in programming or URL syntax

    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
    ConstraintMaker
    -1.11
    IntoConstraints
    -1.02
     الرياضيه
    -0.97
    RetentionPolicy
    -0.88
    RectangleBorder
    -0.88
     estekak
    -0.88
    তথ্যসূত্র
    -0.88
     Efq
    -0.86
     &___
    -0.86
     للمعارف
    -0.86
    POSITIVE LOGITS
    e
    0.52
     list
    0.51
    en
    0.50
     ra
    0.50
     u
    0.49
     general
    0.48
     normal
    0.47
     Sy
    0.47
     lu
    0.47
     Art
    0.47
    Activations Density 0.213%

    No Known Activations