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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10523
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and representations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.55
     Italijanski
    -0.45
     SwitchCompat
    -0.44
     SearchView
    -0.43
     onCreateView
    -0.40
     geslacht
    -0.40
    lapsingToolbar
    -0.40
    CppMethod
    -0.39
    IUrlHelper
    -0.38
     AssemblyVersion
    -0.37
    POSITIVE LOGITS
    addContainerGap
    0.46
    multline
    0.39
    eqnarray
    0.39
    eqn
    0.39
     تمر
    0.39
    Eqn
    0.38
    subequations
    0.38
     concentration
    0.37
    cite
    0.37
    equation
    0.36
    Activations Density 1.286%

    No Known Activations