© 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. 110241
    Prev
    Next
    INDEX
    Explanations

    academic citations and references within a text

    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
     Савезне
    -0.65
    tagHelperRunner
    -0.54
     surla
    -0.52
    MessageOf
    -0.51
    BeginContext
    -0.51
    EndGlobalSection
    -0.51
    hoeddwyd
    -0.50
     noDo
    -0.50
     ModelExpression
    -0.46
    期刊论文
    -0.46
    POSITIVE LOGITS
     planejamento
    0.47
     pageContext
    0.43
     commento
    0.41
     calentamiento
    0.40
     prosím
    0.40
     risico
    0.39
     intentando
    0.39
     chronique
    0.39
     acostumb
    0.38
     charla
    0.38
    Activations Density 0.006%

    No Known Activations