© 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. 31-GEMMASCOPE-RES-16K
    6. 4703
    Prev
    Next
    INDEX
    Explanations

    phrases indicating locations or contextual references within sentences

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

    the word "in" when it appears at the beginning of a clause or sentence to introduce context or a new idea.

    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
     propOrder
    -0.58
    /**
    -0.53
    WriteTagHelper
    -0.51
    ATTER
    -0.50
    TypedDataSet
    -0.50
    ETRIC
    -0.49
    StoryboardSegue
    -0.48
    HtmlAttribute
    -0.47
    eradish
    -0.45
    ThroughAttribute
    -0.43
    POSITIVE LOGITS
     anyways
    0.42
     nutshell
    0.36
     RoutedEventArgs
    0.35
     meanwhile
    0.35
     viewDidLoad
    0.35
     tijden
    0.34
     løpet
    0.34
    forhold
    0.33
     rangka
    0.33
    Anyways
    0.33
    Activations Density 0.437%

    No Known Activations