© 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. 15265
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, particularly "I" and "my"

    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
     our
    -1.31
     we
    -1.26
    Our
    -1.17
     Our
    -1.13
    our
    -1.12
     We
    -1.04
     ourselves
    -1.03
    We
    -1.01
     OUR
    -1.01
    我们的
    -1.00
    POSITIVE LOGITS
    Autoritní
    0.82
    WriteTagHelper
    0.81
     NDEBUG
    0.75
    webElementXpaths
    0.72
    MENAFN
    0.70
    HideFlags
    0.69
     незавершена
    0.69
    aarrggbb
    0.68
    autant
    0.68
    /−
    0.67
    Activations Density 0.199%

    No Known Activations