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. 18-GEMMASCOPE-MLP-65K
    6. 34
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to medical procedures and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.89
    mybatisplus
    -0.82
    fjspx
    -0.82
     faſt
    -0.81
    AutoresizingMask
    -0.81
     Majefty
    -0.79
     ainfi
    -0.77
    ScopeManager
    -0.76
     iſt
    -0.76
     Jefus
    -0.76
    POSITIVE LOGITS
     f
    0.49
     ga
    0.49
     g
    0.48
     code
    0.48
     ins
    0.47
     ir
    0.45
     ba
    0.45
     ref
    0.45
    </caption>
    0.43
     ra
    0.42
    Activations Density 0.229%

    No Known Activations