© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 16434
    Prev
    Next
    INDEX
    Explanations

    mentions of uncertainty or lack of understanding

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

    no idea what/where/how/why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ụng
    -0.35
    lijkse
    -0.35
    劃
    -0.34
    鹹
    -0.33
     Outros
    -0.33
    enumi
    -0.32
    
    -0.32
     Membre
    -0.32
     priced
    -0.32
     verko
    -0.32
    POSITIVE LOGITS
     Ahnung
    0.88
    idea
    0.70
    knows
    0.66
    know
    0.66
     Kenntnis
    0.66
     clue
    0.66
    IDEA
    0.65
     know
    0.65
     knows
    0.64
     idée
    0.63
    Activations Density 0.006%

    No Known Activations