© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121880
    Prev
    Next
    INDEX
    Explanations

    themes related to political and social constructs, particularly focusing on governmental actions, policies, and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.66
    rungsseite
    -0.57
    -------------</
    -0.54
    audiovisuel
    -0.50
     NUKAT
    -0.50
    AddField
    -0.49
    errHandler
    -0.49
    tagext
    -0.49
    CppMethod
    -0.48
     Signalez
    -0.47
    POSITIVE LOGITS
    WithIOException
    0.36
     support
    0.36
    discrimination
    0.35
     recognition
    0.35
     discrimination
    0.33
    AccessFile
    0.33
     blister
    0.33
     honor
    0.32
    support
    0.32
    对待
    0.32
    Activations Density 0.101%

    No Known Activations