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. 1-GEMMASCOPE-MLP-16K
    6. 8751
    Prev
    Next
    INDEX
    Explanations

    terms related to academic programs and accreditation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]').
    -0.57
     ].
    -0.53
    ”.
    -0.53
    ]).
    -0.51
    ].
    -0.51
     }_{\
    -0.50
    ’.
    -0.48
    ']).
    -0.48
    ContentLoaded
    -0.45
    ]].
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    1.14
    rungsseite
    1.11
    TagMode
    1.02
    Personensuche
    1.02
    :✨
    0.97
    SourceChecksum
    0.93
    Personendaten
    0.92
    rawDesc
    0.90
     &___
    0.90
    BeginInit
    0.87
    Activations Density 15.803%

    No Known Activations