© 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
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109346
    Prev
    Next
    INDEX
    Explanations

    references to the concept of uniqueness in data analysis or statistical methods

    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
     Uni
    -2.34
    Uni
    -2.30
     uni
    -1.99
    uni
    -1.95
    UNI
    -1.72
     UNI
    -1.62
     univ
    -1.30
    ユニ
    -1.18
    univ
    -1.15
     UNIV
    -1.09
    POSITIVE LOGITS
    Inconvénients
    0.42
    RTCK
    0.38
    Amicalement
    0.38
     Inscrivez
    0.34
    OkHttpClient
    0.34
    Morfologia
    0.34
    XDECREF
    0.34
    onomía
    0.34
     invokingState
    0.34
     Vrbo
    0.33
    Activations Density 0.004%

    No Known Activations