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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 4961
    Prev
    Next
    INDEX
    Explanations

    references to oil and gas exploration in a geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gonic
    -0.53
    BeforeEach
    -0.52
    Przypisy
    -0.52
     useState
    -0.51
     "..\..\..\
    -0.50
    itope
    -0.49
    ::_('
    -0.49
     الحره
    -0.48
    jspx
    -0.47
    ✨:
    -0.46
    POSITIVE LOGITS
     prospecting
    0.82
     geologists
    0.69
     geolog
    0.68
     geologist
    0.68
     mining
    0.65
     geologic
    0.64
     geological
    0.61
     operators
    0.60
     operator
    0.59
     Operator
    0.59
    Activations Density 0.210%

    No Known Activations