© 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. 10703
    Prev
    Next
    INDEX
    Explanations

    nested structures or references, such as parentheses and brackets

    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
    HideFlags
    -1.11
    хьтан
    -1.08
     Мексичка
    -1.05
     itſelf
    -1.04
     lenker
    -1.03
     &___
    -1.01
     createContext
    -1.00
     oprot
    -0.94
    Šaltiniai
    -0.92
     myſelf
    -0.91
    POSITIVE LOGITS
     (
    0.70
    <eos>
    0.67
    <
    0.61
    ↵
    0.56
    ms
    0.53
    (
    0.53
    ?
    0.50
    if
    0.50
     <
    0.50
    ↵↵
    0.50
    Activations Density 0.117%

    No Known Activations