© 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. 109275
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and functions within a scientific or technical context

    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
     gynhyrchwyd
    -1.03
    parsedMessage
    -0.98
    GEBURTSDATUM
    -0.98
     ProtoMessage
    -0.94
    tagHelperRunner
    -0.93
    protoimpl
    -0.88
    AddTagHelper
    -0.88
    Personendaten
    -0.88
    UnsafeEnabled
    -0.87
     OMITBAD
    -0.86
    POSITIVE LOGITS
    *
    0.30
    iii
    0.27
     jul
    0.26
     oh
    0.26
     Administración
    0.25
    queles
    0.25
     normalidad
    0.24
    势
    0.23
     dấu
    0.23
    ii
    0.22
    Activations Density 0.224%

    No Known Activations