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. 6-GEMMASCOPE-MLP-16K
    6. 53
    Prev
    Next
    INDEX
    Explanations

    references to achievements or milestones in sports and architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    fromnode
    -0.49
     where
    -0.45
    ranti
    -0.44
    where
    -0.43
    みる
    -0.43
    經常
    -0.41
    matics
    -0.41
    active
    -0.40
    jela
    -0.40
    puts
    -0.40
    POSITIVE LOGITS
     صوتيه
    1.01
    #+#
    0.93
    ########.
    0.85
     الحره
    0.85
    :+:
    0.72
     propOrder
    0.71
     ویکی‌پدیا
    0.69
     Efq
    0.69
     ویکی‌پدیای
    0.68
     مشين
    0.68
    Activations Density 0.423%

    No Known Activations