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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31855
    Prev
    Next
    INDEX
    Explanations

    references to the author or speaker using the term "Me"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colgantes
    -0.50
     normalidad
    -0.49
    ņas
    -0.47
     wikipagina
    -0.47
     oorsp
    -0.46
     Infór
    -0.46
     nasled
    -0.45
     Italij
    -0.45
     Fassung
    -0.45
     zimowa
    -0.45
    POSITIVE LOGITS
    Me
    2.05
     Me
    2.03
     ME
    1.09
    ME
    0.97
    Meik
    0.93
     Megal
    0.91
     Mejía
    0.89
     Ме
    0.85
    me
    0.80
    Ме
    0.79
    Activations Density 0.005%

    No Known Activations