© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110116
    Prev
    Next
    INDEX
    Explanations

    various syntactic patterns and special characters in technical or scientific contexts

    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
     cliquez
    -0.34
    fjspx
    -0.33
    在她
    -0.25
     yyj
    -0.25
     templado
    -0.24
    Quic
    -0.24
    FieldOffsetTable
    -0.24
     selamat
    -0.24
    aarrggbb
    -0.24
     procurar
    -0.23
    POSITIVE LOGITS
     محفوظة
    0.67
    出版年
    0.60
    Lähteet
    0.58
    SPJ
    0.58
     שוליים
    0.57
     كومونز
    0.56
    OGND
    0.56
    Архівовано
    0.53
    TagMode
    0.52
    CGRectMake
    0.51
    Activations Density 0.000%

    No Known Activations