© 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. 110225
    Prev
    Next
    INDEX
    Explanations

    specific names and identifiers, likely associated with legal and 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
    ర్
    -1.27
    র্
    -1.23
    र्
    -1.21
    ર્
    -1.17
    ರ್
    -1.12
    ർ
    -1.00
    ര്‍
    -1.00
    ர்
    -0.90
     незавершена
    -0.78
     Chwiliwch
    -0.76
    POSITIVE LOGITS
     poffe
    0.36
     cal
    0.35
     express
    0.33
     متعلقه
    0.32
     conven
    0.29
     aten
    0.29
    movq
    0.28
     hard
    0.28
    zeptember
    0.28
    zám
    0.28
    Activations Density 0.002%

    No Known Activations