© 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. 3-GEMMASCOPE-RES-16K
    11. 16001
    Prev
    Next
    INDEX
    Explanations

    coding patterns and structures in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -1.11
    +#+#
    -1.07
    fjspx
    -0.85
    mybatisplus
    -0.84
     >=",
    -0.82
    Diwedd
    -0.82
     becauſe
    -0.81
    providedIn
    -0.78
    GraphicsUnit
    -0.77
     SafeMath
    -0.76
    POSITIVE LOGITS
    ↵↵
    0.87
    ↵
    0.59
     etc
    0.58
      
    0.54
    UnusedPrivate
    0.53
    ↵↵↵
    0.52
    .
    0.52
    ↵↵↵↵
    0.52
    Hentet
    0.52
    etc
    0.52
    Activations Density 0.330%

    No Known Activations