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. 34
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terminology related to calculus and probability

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

    mathematical terms and symbols related to integrals and exponential functions

    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
    OGND
    -0.92
    MigrationBuilder
    -0.71
     nahilalakip
    -0.68
    oredCriteria
    -0.66
    jsxFileName
    -0.66
     unknownFields
    -0.64
    ruptedException
    -0.61
    noy
    -0.59
     Roskov
    -0.59
    adaptiveStyles
    -0.58
    POSITIVE LOGITS
    ={`/
    0.56
    writeField
    0.56
    ieteur
    0.52
    endphp
    0.51
    sonaro
    0.51
     décé
    0.51
    </tfoot>
    0.49
    lotl
    0.48
    риях
    0.48
    ⓧ
    0.47
    Activations Density 0.825%

    No Known Activations