© 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. 12785
    Prev
    Next
    INDEX
    Explanations

    phrases that convey the relationship between different entities or systems

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

    pairs or groups of items that are linked or paired together through the word "associated" or similar relational 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
     propOrder
    -0.76
     oprot
    -0.55
    complexType
    -0.54
    IsContent
    -0.54
    webElementXpaths
    -0.54
     myſelf
    -0.52
    exitRule
    -0.50
    Kjelder
    -0.49
    ſelves
    -0.48
    MigrationBuilder
    -0.48
    POSITIVE LOGITS
     associated
    1.99
     associate
    1.77
     associating
    1.74
     association
    1.66
     associ
    1.64
    associated
    1.63
     asoci
    1.56
     attached
    1.55
     Associated
    1.54
     asociado
    1.53
    Activations Density 0.797%

    No Known Activations