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. 23
    Prev
    Next
    INDEX
    Explanations

    urgent calls to action or directives

    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
    ⓧ
    -0.65
    addCriterion
    -0.54
    onedDateTime
    -0.52
    ">//
    -0.50
    [--
    -0.49
     Luego
    -0.49
    évaluateur
    -0.47
    큼
    -0.47
     demikian
    -0.46
    γη
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    XmlAccessType
    0.62
    ########.
    0.59
    GetKeyDown
    0.56
     wireType
    0.56
     CWE
    0.56
     HttpNotFound
    0.55
    UnsafeEnabled
    0.53
     Италијани
    0.53
     iprot
    0.51
    Activations Density 0.314%

    No Known Activations