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. 37
    Prev
    Next
    INDEX
    Explanations

    references to Ukraine

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

    mentions of Ukraine

    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
    ."]
    -0.67
     Ukraine
    -0.67
    );*/
    -0.66
    ")}
    -0.66
    ')}
    -0.65
    ''')
    -0.65
    :])
    -0.65
    });*/
    -0.65
    .」
    -0.64
     edn
    -0.63
    POSITIVE LOGITS
    تقاوى
    0.75
    Datuak
    0.69
     EClass
    0.67
    migrationBuilder
    0.66
     रेटिंग
    0.55
     CHtml
    0.53
    VIAF
    0.53
    featureID
    0.52
    IContainer
    0.52
    OrBuilder
    0.52
    Activations Density 0.146%

    No Known Activations