© 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. 14130
    Prev
    Next
    INDEX
    Explanations

    functions or methods defined as public in code

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

    PHP function declarations (specifically the `public` keyword at the start of function definitions).

    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
    WriteBarrier
    -0.56
     esternos
    -0.52
    Parcelize
    -0.51
    ynchronously
    -0.50
    RTLI
    -0.47
    HomeAsUpEnabled
    -0.47
    IGraphics
    -0.47
     themſelves
    -0.47
     $_[
    -0.47
    PyExc
    -0.46
    POSITIVE LOGITS
     function
    0.79
    function
    0.60
     functioning
    0.43
     Function
    0.43
     función
    0.41
     fonction
    0.40
     функ
    0.38
    hopped
    0.38
     funktion
    0.37
     functioned
    0.37
    Activations Density 0.046%

    No Known Activations