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-2-2B
    4. MLP Out - 65k
    5. 4-GEMMASCOPE-MLP-65K
    6. 82
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.53
    ShortName
    -0.49
    enumi
    -0.47
    --)
    
    -0.47
    varing
    -0.46
     berguna
    -0.46
    opha
    -0.43
     tutoring
    -0.43
    ündete
    -0.42
    Schedulers
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.93
     ProtoMessage
    0.68
     ComVisible
    0.68
    Geplaatst
    0.66
    Cyfeiriadau
    0.66
    DoubleQuotes
    0.65
    Референце
    0.64
     AssemblyCulture
    0.62
    kloped
    0.60
    AxisAlignment
    0.59
    Activations Density 0.029%

    No Known Activations