© 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. 2-GEMMASCOPE-RES-16K
    6. 1912
    Prev
    Next
    INDEX
    Explanations

    references to the concept of an 'idea' or 'concept'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ならない
    -0.61
    Listar
    -0.58
    webElementGuid
    -0.58
    ng
    -0.57
    页面存档备份
    -0.57
    วน
    -0.56
     competente
    -0.53
    確実に
    -0.53
     Hang
    -0.52
    しっかりと
    -0.51
    POSITIVE LOGITS
     idea
    3.97
     Idea
    3.45
    Idea
    3.34
    idea
    3.25
     IDEA
    2.89
     idée
    2.73
     ideia
    2.68
     Idee
    2.65
    idée
    2.52
     ideas
    2.50
    Activations Density 0.145%

    No Known Activations