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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2796
    Prev
    Next
    INDEX
    Explanations

    academic references and attributes related to mathematical concepts and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic reference citations and bibliographic metadata.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.47
    propto
    -0.43
    aarrggbb
    -0.42
    ParallelGroup
    -0.42
    addGap
    -0.39
     onBind
    -0.38
    <?
    -0.38
    DebuggerNonUser
    -0.38
     StatefulWidget
    -0.36
    AxisAlignment
    -0.36
    POSITIVE LOGITS
     mathematicians
    0.71
     mathematics
    0.64
     Mathematics
    0.56
     mathematical
    0.54
     mathematician
    0.53
    mathematics
    0.53
    Carriera
    0.53
     Math
    0.52
     math
    0.51
     Mathematical
    0.50
    Activations Density 1.169%

    No Known Activations