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. 3473
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to honesty and integrity

    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
    er
    -0.84
     kæ
    -0.76
    mė
    -0.75
     Dougherty
    -0.70
    ValueStyle
    -0.69
    SpringBootTest
    -0.67
    raman
    -0.65
    Gly
    -0.65
     Andrade
    -0.64
    lblNewLabel
    -0.63
    POSITIVE LOGITS
    expandindo
    1.00
     protoimpl
    0.95
    DebuggerNonUser
    0.90
     propOrder
    0.89
     Wallis
    0.88
    İstinadlar
    0.88
    Wallis
    0.88
               
    0.87
     ―――――
    0.86
    RenderAtEndOf
    0.85
    Activations Density 0.130%

    No Known Activations