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. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3797
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to engineering and machinery systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.52
     
    -0.48
    RegressionTest
    -0.46
    ICOLON
    -0.44
     Ba
    -0.43
    </strong>
    -0.42
    <eos>
    -0.40
     “
    -0.39
    новништво
    -0.39
    '
    -0.38
    POSITIVE LOGITS
     Monfieur
    0.91
     Shakspeare
    0.86
    WebServlet
    0.75
    MigrationBuilder
    0.74
     vectorielle
    0.72
    eterangan
    0.70
     StringTokenizer
    0.70
     métallique
    0.69
     Cæsar
    0.69
     Mahomet
    0.69
    Activations Density 1.335%

    No Known Activations