Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 34639
    Prev
    Next
    INDEX
    Explanations

    references to modal verbs and their usage in various contexts

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

    German "da-" prepositions or adverbs

    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
    RegressionTest
    -0.78
    
    -0.69
     feroit
    -0.69
    hoeddwyd
    -0.69
     enfans
    -0.66
     ویکی‌پدی
    -0.66
    GEBURTSDATUM
    -0.66
     auroit
    -0.65
    ſt
    -0.62
     estadounid
    -0.61
    POSITIVE LOGITS
     dafür
    1.20
     dazu
    1.15
     Dafür
    0.93
     darauf
    0.90
     darüber
    0.88
     davon
    0.79
     daran
    0.76
    Dazu
    0.74
     Dazu
    0.71
     damit
    0.70
    Activations Density 0.004%

    No Known Activations