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. 109652
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to biological and chemical processes

    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
    VYMaps
    -0.54
    dead
    -0.47
     Dada
    -0.47
    oredCriteria
    -0.47
    Selfer
    -0.44
     Schmitz
    -0.44
     Volkes
    -0.44
    ISODE
    -0.44
    dad
    -0.43
    Driver
    -0.42
    POSITIVE LOGITS
    EndInit
    0.48
    AndEndTag
    0.47
    ApiProperty
    0.45
    RectangleBorder
    0.39
    FromArgb
    0.35
    ContentLoaded
    0.35
     ActionListener
    0.35
    sief
    0.34
    """,
    0.34
     مرئيه
    0.33
    Activations Density 0.019%

    No Known Activations