© 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. 25-GEMMASCOPE-RES-16K
    11. 1261
    Prev
    Next
    INDEX
    Explanations

    issues related to customer service experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.65
    tagHelperRunner
    -0.64
     umumnya
    -0.58
    exitRule
    -0.56
    {:
    -0.55
     quelquefois
    -0.55
     meist
    -0.54
    ("/{
    -0.54
     tends
    -0.54
    近年
    -0.53
    POSITIVE LOGITS
     supuestamente
    0.88
     told
    0.81
     Told
    0.80
     supposedly
    0.76
     Apparently
    0.73
    🤬
    0.72
     katanya
    0.72
     THEY
    0.70
    Apparently
    0.68
    told
    0.68
    Activations Density 0.309%

    No Known Activations