© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8880
    Prev
    Next
    INDEX
    Explanations

    references to the word "Lo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    Portály
    -0.53
    الحياه
    -0.53
    TestingModule
    -0.51
     Roskov
    -0.50
    hyrchwyd
    -0.47
    mybatisplus
    -0.46
    сылкі
    -0.45
    postsleuth
    -0.44
     initComponents
    -0.44
    ьаж
    -0.43
    POSITIVE LOGITS
     Lo
    2.52
    Lo
    2.28
     lo
    2.14
    lo
    2.05
     LO
    1.80
    LO
    1.55
     lobe
    1.02
     Ло
    0.95
    lobe
    0.94
     ло
    0.93
    Activations Density 1.039%

    No Known Activations