© 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. 4025
    Prev
    Next
    INDEX
    Explanations

    substructures or hierarchical relationships in data

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

    hierarchical subdivision structures and nested categorization language.

    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
     AssemblyCompany
    -0.55
    migrationBuilder
    -0.55
    MLLoader
    -0.54
     iprot
    -0.52
    yntaxException
    -0.52
     Geſch
    -0.51
    يميديا
    -0.51
    atguigu
    -0.51
    pecabe
    -0.51
    contentLoaded
    -0.50
    POSITIVE LOGITS
     sub
    2.86
     Sub
    2.22
    sub
    2.22
    Sub
    2.06
     SUB
    1.89
    サブ
    1.84
    SUB
    1.74
     getSub
    1.63
    getSub
    1.61
     subs
    1.58
    Activations Density 1.200%

    No Known Activations