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. 0-GEMMASCOPE-MLP-16K
    6. 70
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "place" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to the concept of "place."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initWithFrame
    -0.73
     uſ
    -0.69
    ไง
    -0.68
    Diweddarwch
    -0.66
     Houſe
    -0.65
    VIAF
    -0.65
     myſelf
    -0.65
     raiſ
    -0.65
     '\\;'
    -0.63
    )?;
    -0.63
    POSITIVE LOGITS
    外部リンク
    0.57
    зулта
    0.56
    Alike
    0.55
    TypedDataSet
    0.52
    靡
    0.50
    genza
    0.48
    awaiter
    0.47
    -\
    0.47
     ***!
    0.47
    TableHead
    0.46
    Activations Density 0.170%

    No Known Activations