Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15653
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and concepts related to medical conditions, statistics, and physical phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    -1.17
    k
    -1.15
    l
    -1.05
    t
    -1.04
    r
    -1.03
    m
    -1.00
    ng
    -0.95
    p
    -0.94
    s
    -0.93
    ling
    -0.91
    POSITIVE LOGITS
     LDA
    1.14
    tvguidetime
    1.10
    annica
    1.09
    drawal
    1.05
     ITA
    1.03
     TDA
    1.02
     SNA
    1.02
     NTA
    1.01
    esterday
    1.01
    polation
    1.01
    Activations Density 1.341%

    No Known Activations