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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105437
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the number zero

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.45
     Artículos
    -0.40
     two
    -0.38
     Menggunakan
    -0.37
    دانلود
    -0.37
    :
    -0.37
     utilizing
    -0.36
     作者
    -0.35
     Zusammen
    -0.34
     Utilizamos
    -0.34
    POSITIVE LOGITS
    0
    1.23
    0
    0.65
    /**
    0.64
    majánló
    0.61
    ০
    0.59
    𝟬
    0.58
    Zero
    0.57
     Zero
    0.57
     零
    0.57
     ORO
    0.56
    Activations Density 0.022%

    No Known Activations