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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109702
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their variations indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    écnicas
    -0.35
    ene
    -0.35
     Aufen
    -0.35
     Fo
    -0.35
    tt
    -0.34
     ağır
    -0.34
    otto
    -0.34
    igh
    -0.33
     Stille
    -0.33
     crochê
    -0.32
    POSITIVE LOGITS
    UrlResolution
    0.72
     autorytatywna
    0.70
     للمعارف
    0.68
    ImageContext
    0.65
    IntoConstraints
    0.63
    Datuak
    0.60
     oprot
    0.60
     CWE
    0.60
    AndEndTag
    0.59
    anyahu
    0.57
    Activations Density 0.017%

    No Known Activations