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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8755
    Prev
    Next
    INDEX
    Explanations

    descriptions of residential properties and their amenities

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

    descriptive text about residential property amenities and features.

    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
     dodgy
    -0.36
      
    -0.36
    ッズ
    -0.29
     blog
    -0.28
     apparently
    -0.28
     specific
    -0.27
     fake
    -0.27
     tal
    -0.27
     dis
    -0.26
    ToAction
    -0.26
    POSITIVE LOGITS
    OGND
    0.75
    ChildScrollView
    0.73
     kasarigan
    0.71
    !***
    0.70
    səhifə
    0.69
     autorytatywna
    0.69
     estekak
    0.68
     محفوظة
    0.68
     المعيارى
    0.67
    󰀄
    0.66
    Activations Density 0.074%

    No Known Activations