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 - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8761
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to gas mechanisms and combustion processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.69
     mérite
    -0.53
    VersionUID
    -0.52
     merec
    -0.52
    Datuak
    -0.51
     lenker
    -0.51
     métallique
    -0.51
    saraba
    -0.51
    ondata
    -0.50
    ]`
    -0.50
    POSITIVE LOGITS
     SwitchCompat
    0.62
    exitRule
    0.58
    метров
    0.57
    HandlerContext
    0.54
    monary
    0.53
     rest
    0.53
    glLoadIdentity
    0.53
    Odor
    0.50
    ollectionView
    0.48
    Odour
    0.47
    Activations Density 0.359%

    No Known Activations