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. 35
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to legal matters and social justice

    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
    -0.94
     ExecuteAsync
    -0.90
    ScopeManager
    -0.86
     >=",
    -0.85
    #+#
    -0.84
    Brainz
    -0.84
    makeConstraints
    -0.82
     betweenstory
    -0.81
     Parenthood
    -0.78
    ArgsConstructor
    -0.78
    POSITIVE LOGITS
    zondere
    0.49
    ROGEN
    0.42
    ova
    0.41
     …
    0.39
     Bo
    0.37
     kalangan
    0.36
     The
    0.36
     this
    0.35
     and
    0.35
    OCI
    0.35
    Activations Density 10.173%

    No Known Activations