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. 59
    Prev
    Next
    INDEX
    Explanations

    occurrences of the second person and first person pronouns

    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
    ISupport
    -0.52
    aktur
    -0.49
     ihr
    -0.44
     nærm
    -0.43
    ianus
    -0.43
     préf
    -0.43
     précieux
    -0.42
    Lookup
    -0.42
    yethyl
    -0.41
    ptonshire
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.81
     BoxFit
    0.81
     Мексичка
    0.75
    ArrowToggle
    0.75
     الرياضيه
    0.74
     Efq
    0.74
     protoimpl
    0.72
    Kjelder
    0.70
     beginnetje
    0.69
    ագրություններ
    0.68
    Activations Density 0.175%

    No Known Activations