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. 22-GEMMASCOPE-MLP-16K
    6. 15878
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational tools and support mechanisms for students' writing skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.75
    usercontent
    -0.68
     educativas
    -0.54
    +#+#
    -0.54
    TableHead
    -0.52
    principalTable
    -0.52
     cherchés
    -0.51
     ThemeData
    -0.49
     permita
    -0.49
    Education
    -0.48
    POSITIVE LOGITS
    Sinon
    0.53
     Conferences
    0.53
     scaffolding
    0.52
    ttino
    0.52
    WEBPACK
    0.52
     model
    0.52
     conferences
    0.52
     Gost
    0.51
     scaffolds
    0.50
    Expert
    0.49
    Activations Density 0.264%

    No Known Activations