© 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. 110037
    Prev
    Next
    INDEX
    Explanations

    references to time periods and calendar-related terms

    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
     AssemblyCulture
    -0.76
    ChildScrollView
    -0.65
     resourceCulture
    -0.62
    tonsoft
    -0.59
     GenerationType
    -0.59
    UrlResolution
    -0.59
     виправивши
    -0.52
    DataAnnotations
    -0.52
     contextLoads
    -0.52
     JADX
    -0.52
    POSITIVE LOGITS
    SOUNDBITE
    0.36
    guisement
    0.36
     canst
    0.35
    Abit
    0.33
     resc
    0.30
     pete
    0.30
    ſelf
    0.30
     getBase
    0.30
    Tops
    0.29
    損
    0.29
    Activations Density 0.077%

    No Known Activations