© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31163
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Mary" and its variations

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

    Mary, Maria, Marie

    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
    findpost
    -0.58
     Photocase
    -0.51
    ьаж
    -0.51
    pantalón
    -0.50
    CppCodeGen
    -0.47
     habet
    -0.47
    WriteBarrier
    -0.46
    CardContent
    -0.46
    patrón
    -0.45
    BitConverter
    -0.45
    POSITIVE LOGITS
     Mary
    1.58
    Mary
    1.45
     mary
    1.43
     Maria
    1.42
     MARY
    1.37
     María
    1.33
    Maria
    1.28
    MARY
    1.23
     maria
    1.20
    mary
    1.18
    Activations Density 0.003%

    No Known Activations