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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109623
    Prev
    Next
    INDEX
    Explanations

    proper nouns and key technical terms

    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
    ใช้
    -1.38
    ใช
    -0.79
     ใช้
    -0.75
     dùng
    -0.63
     незавершена
    -0.57
    WithIOException
    -0.49
    postsleuth
    -0.47
    Portail
    -0.47
    LookAnd
    -0.45
    ใช้งาน
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.69
     OMITBAD
    0.46
    >--}}
    0.44
    }}]{
    0.41
     Paglinawan
    0.41
    твра
    0.40
    InBytes
    0.40
     intéress
    0.40
     eingesch
    0.39
    yaret
    0.39
    Activations Density 0.000%

    No Known Activations