© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 732
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming functions and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    commands and operations related to managing email or data frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    automatic detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marginHorizontal
    -0.52
    rawDesc
    -0.44
    MockMvc
    -0.43
    通路
    -0.41
    edes
    -0.40
     angegeben
    -0.40
     bougies
    -0.40
    ForTesting
    -0.39
     investissement
    -0.38
     muzzle
    -0.38
    POSITIVE LOGITS
     automatically
    1.43
     automatic
    1.23
     Automatically
    1.20
    automatically
    1.14
     detect
    1.11
     detects
    1.10
     auto
    1.09
     recognize
    1.08
     AUTOMATIC
    1.07
     Automatic
    1.06
    Activations Density 0.684%

    No Known Activations