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. 9-GEMMASCOPE-RES-16K
    6. 1551
    Prev
    Next
    INDEX
    Explanations

    terms related to desperation and failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TagMode
    -0.68
    Kontrola
    -0.67
     recommandée
    -0.64
    ьаж
    -0.63
     GetEnumerator
    -0.60
    AutoresizingMask
    -0.58
     незавершена
    -0.58
    timewa
    -0.56
    rikes
    -0.54
    AccessorTable
    -0.53
    POSITIVE LOGITS
     crappy
    0.79
    poor
    0.75
     rudimentary
    0.74
     poor
    0.73
     dilapidated
    0.72
     shitty
    0.71
     worse
    0.68
    Poor
    0.66
     cheap
    0.66
     feeble
    0.66
    Activations Density 0.515%

    No Known Activations