© 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. 9947
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate construction or assembly

    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
     ExecuteAsync
    -0.94
     незавершена
    -0.80
     utafitiHapana
    -0.75
    TintMode
    -0.74
    ━━━━━━━━
    -0.74
     PMS
    -0.73
    elemField
    -0.73
     Pager
    -0.72
     PeEnEo
    -0.72
    ThroughAttribute
    -0.72
    POSITIVE LOGITS
     built
    2.58
     Built
    2.40
    Built
    2.40
    built
    2.37
     BUILT
    2.31
    BUILT
    2.01
     builtin
    1.47
     construido
    1.23
    Builtin
    1.14
     constructed
    1.11
    Activations Density 0.050%

    No Known Activations