Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 7668
    Prev
    Next
    INDEX
    Explanations

    concepts related to dependency injection and method registration in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessFile
    -0.62
    esgue
    -0.51
     Pauli
    -0.50
     chrom
    -0.49
    sidian
    -0.49
     Geller
    -0.48
    xdr
    -0.48
     Rass
    -0.47
    htaccess
    -0.47
    odat
    -0.46
    POSITIVE LOGITS
     injection
    1.08
     inject
    1.07
     Inject
    1.06
     Injection
    1.04
    Inject
    0.96
    inject
    0.96
     injecting
    0.96
    Injection
    0.96
     injected
    0.95
     injector
    0.94
    Activations Density 0.280%

    No Known Activations