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. 109568
    Prev
    Next
    INDEX
    Explanations

    references to specific names and significant events or entities

    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
     utafitiHapana
    -0.76
    +#+#
    -0.74
    fjspx
    -0.58
    AndEndTag
    -0.57
    verifyException
    -0.56
    FieldBuilder
    -0.54
     OMITBAD
    -0.54
    featureID
    -0.54
    oa̍t
    -0.54
    parsedMessage
    -0.54
    POSITIVE LOGITS
     aimez
    0.37
     unterwegs
    0.30
    gründet
    0.29
    oluble
    0.29
    tight
    0.29
    ppuden
    0.29
     Tight
    0.28
    ख़
    0.28
     yumu
    0.28
     Hombre
    0.26
    Activations Density 0.001%

    No Known Activations