© 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. 5-GEMMASCOPE-RES-16K
    11. 13771
    Prev
    Next
    INDEX
    Explanations

    evidence related to claims or observations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.88
     Administrativna
    -0.86
    AsUp
    -0.77
    MENAFN
    -0.76
    DeleteBehavior
    -0.74
    mybatisplus
    -0.73
     ModelExpression
    -0.73
     arşivlendi
    -0.72
     betweenstory
    -0.72
    CppMethod
    -0.71
    POSITIVE LOGITS
     manifested
    0.56
     evidenced
    0.54
     me
    0.48
     evident
    0.47
     the
    0.45
     manifest
    0.45
    manif
    0.43
     exemplified
    0.42
     evidente
    0.42
    withId
    0.42
    Activations Density 0.424%

    No Known Activations