© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6460
    Prev
    Next
    INDEX
    Explanations

    key mathematical properties and terms related to structures and functions in algebraic contexts

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

    commas that appear after mathematical or technical expressions.

    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
     followed
    -0.47
     subsequent
    -0.47
    followed
    -0.46
     Subsequent
    -0.44
     Later
    -0.44
    Later
    -0.43
     Followed
    -0.43
    <bos>
    -0.42
     later
    -0.41
     Subsequently
    -0.40
    POSITIVE LOGITS
     then
    2.36
     entonces
    2.05
     allora
    2.03
     então
    1.91
     alors
    1.77
    then
    1.74
    Then
    1.63
     Then
    1.59
     thì
    1.59
     тогда
    1.49
    Activations Density 0.683%

    No Known Activations