Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3121
    Prev
    Next
    INDEX
    Explanations

    expressions of fatigue and weariness related to various situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.78
    AndEndTag
    -0.65
    StoryboardSegue
    -0.61
     Fond
    -0.54
     Nearest
    -0.53
     heu
    -0.53
     Skor
    -0.52
     Recom
    -0.51
     Widely
    -0.51
     reccomend
    -0.51
    POSITIVE LOGITS
    ensement
    0.63
     frustration
    0.63
    AlterField
    0.61
     frustrations
    0.61
     exas
    0.58
     exasperated
    0.58
    reszcie
    0.56
     терпе
    0.55
    hoga
    0.54
    够了
    0.53
    Activations Density 0.196%

    No Known Activations