© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11638
    Prev
    Next
    INDEX
    Explanations

    programming constructs and library includes related to Boost, particularly in the context of C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.59
     protoimpl
    -0.57
    StandardCharsets
    -0.57
    UrlResolution
    -0.49
     apo
    -0.48
     AppCompat
    -0.46
    TestingModule
    -0.45
    noinspection
    -0.45
    AddTagHelper
    -0.45
    Datuak
    -0.45
    POSITIVE LOGITS
     boost
    0.74
    boost
    0.71
     Boost
    0.63
     boosting
    0.53
    cout
    0.52
    Boost
    0.52
    BOOST
    0.50
     vector
    0.50
    ::
    0.50
    ::~
    0.47
    Activations Density 1.039%

    No Known Activations