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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4208
    Prev
    Next
    INDEX
    Explanations

    sections of text marked with comments or formatting syntax

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

    opening brackets or delimiters at the start of new sections or code blocks.

    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
    AddTagHelper
    -0.63
     Administrativna
    -0.57
     архивлан
    -0.54
    kheim
    -0.51
    XmlAccessorType
    -0.51
     autorytatywna
    -0.51
    Parcelize
    -0.51
    ffine
    -0.50
     pas
    -0.50
    DllImport
    -0.49
    POSITIVE LOGITS
    adaptiveStyles
    0.39
     automático
    0.36
     &___
    0.36
    CrossRef
    0.35
    发表于
    0.35
    tagHelperRunner
    0.34
    RegressionTest
    0.33
     scolaires
    0.32
    Comentários
    0.32
    saraba
    0.31
    Activations Density 0.009%

    No Known Activations