© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1752
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize personal experiences or opinions expressed with "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    ReusableCell
    -1.11
     فريبيس
    -0.94
     виправивши
    -0.85
    Portail
    -0.85
     HttpNotFound
    -0.83
     disambiguazione
    -0.83
    mybatisplus
    -0.83
     AssemblyVersion
    -0.82
     GlobalKey
    -0.81
     useAppContext
    -0.81
    POSITIVE LOGITS
    I
    1.44
     I
    0.92
    We
    0.86
    It
    0.83
    i
    0.79
    My
    0.76
    The
    0.73
    In
    0.70
    This
    0.67
    You
    0.67
    Activations Density 0.126%

    No Known Activations