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. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109946
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "potentially."

    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
     potentially
    -1.05
    potentially
    -0.95
    Pot
    -0.57
    entially
    -0.54
    yntaxException
    -0.53
    دانشنامهٔ
    -0.53
     Pot
    -0.52
     hırka
    -0.50
    uncios
    -0.50
    Possibly
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.70
    WriteLiteral
    0.42
    SpringBootTest
    0.42
    #+#
    0.42
    rungsseite
    0.40
    omock
    0.40
    tonode
    0.40
    出版年
    0.39
    Atsauces
    0.39
    abestanden
    0.39
    Activations Density 0.003%

    No Known Activations