© 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. 31-GEMMASCOPE-RES-131K
    6. 111234
    Prev
    Next
    INDEX
    Explanations

    themes related to music, devotion, and spiritual practices

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

    poem and poetry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.70
     NSCoder
    -0.63
     للاسماء
    -0.55
     مشين
    -0.52
    tvguidetime
    -0.49
    mybatisplus
    -0.48
     BoxFit
    -0.48
    numerusform
    -0.47
     AssemblyCulture
    -0.45
     CanadaChoose
    -0.45
    POSITIVE LOGITS
     poem
    1.18
     poems
    1.05
     poetry
    0.98
     poème
    0.94
    poem
    0.89
     Poem
    0.88
     puisi
    0.86
     Gedicht
    0.85
     poemas
    0.83
     Poems
    0.81
    Activations Density 0.035%

    No Known Activations