© 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. 45794
    Prev
    Next
    INDEX
    Explanations

    mentions of 'Son' or variations of the term related to either a character or specific context in different settings

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

    SONOS transistors

    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
     ganchillo
    -0.47
    ########.
    -0.47
    rzez
    -0.45
    ctique
    -0.45
    cetines
    -0.45
     democrática
    -0.44
     censi
    -0.43
     kentang
    -0.42
     roulant
    -0.42
    iyle
    -0.41
    POSITIVE LOGITS
     Son
    2.11
    Son
    2.03
     SON
    1.70
     Sons
    1.21
     Sonata
    1.17
     Sonora
    1.12
     Sonar
    1.09
     Sono
    1.05
     Sonn
    1.05
    SON
    1.05
    Activations Density 0.006%

    No Known Activations