© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104223
    Prev
    Next
    INDEX
    Explanations

    expressions indicating consistency or universality in conditions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Init
    -0.38
     noted
    -0.38
    osidad
    -0.36
     Later
    -0.35
     note
    -0.35
    意
    -0.34
    ngOnInit
    -0.33
    addAttribute
    -0.33
    Initi
    -0.32
    想想
    -0.32
    POSITIVE LOGITS
     ALWAYS
    0.73
    ALWAYS
    0.69
    IsContent
    0.69
    всегда
    0.69
    always
    0.69
    Datuak
    0.68
     <<<<<<<<<<<<<<
    0.68
    DockStyle
    0.67
     always
    0.66
    دانشنامهٔ
    0.65
    Activations Density 0.077%

    No Known Activations