© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11427
    Prev
    Next
    INDEX
    Explanations

    terms related to development and growth processes

    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
    onucle
    -0.55
    ullaby
    -0.52
    bibliothek
    -0.51
    mybatisplus
    -0.50
    mobileqq
    -0.50
     NUnit
    -0.49
    bootstrapcdn
    -0.49
    illots
    -0.48
    IUCN
    -0.48
     Điện
    -0.48
    POSITIVE LOGITS
     development
    2.38
    develop
    2.30
     develop
    2.19
    development
    2.18
     developing
    2.17
     develops
    2.16
    Develop
    2.15
    Development
    2.15
     DEVELOP
    2.14
     Development
    2.10
    Activations Density 0.152%

    No Known Activations