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. 7-GEMMASCOPE-RES-16K
    6. 14659
    Prev
    Next
    INDEX
    Explanations

    terms related to decline and deterioration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.66
     bosques
    -0.60
    n
    -0.58
     Draht
    -0.58
    制
    -0.58
    𝘣
    -0.58
     spacers
    -0.58
    yanka
    -0.57
     areia
    -0.57
    mobileqq
    -0.57
    POSITIVE LOGITS
     decline
    1.03
     Decay
    1.02
     decay
    0.99
    decay
    0.95
    发表于
    0.90
    Decay
    0.89
     decays
    0.88
     Decline
    0.88
     declines
    0.88
     deterioration
    0.87
    Activations Density 0.311%

    No Known Activations