© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2945
    Prev
    Next
    INDEX
    Explanations

    negative expressions or phrases indicating misfortune or regret

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

    expressions of regret or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sarm
    -0.65
     ECR
    -0.62
     cps
    -0.60
     varför
    -0.56
     OPP
    -0.55
     DLP
    -0.55
     MCM
    -0.54
    Rost
    -0.54
    why
    -0.54
     %>%
    -0.53
    POSITIVE LOGITS
    Tembelea
    0.75
    SourceChecksum
    0.73
     оригіналу
    0.73
    ureusement
    0.67
     ligiloj
    0.65
    heureusement
    0.62
    Leider
    0.62
    roppo
    0.62
    iestety
    0.62
    värr
    0.61
    Activations Density 0.104%

    No Known Activations