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. 11-GEMMASCOPE-RES-16K
    6. 6411
    Prev
    Next
    INDEX
    Explanations

    situations related to confinement and feelings of stagnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     урна
    -0.50
    }}/>
    -0.48
     endforeach
    -0.47
     dynamic
    -0.45
    endforeach
    -0.44
    IERC
    -0.42
     conviction
    -0.41
    味噌汁
    -0.40
     Wray
    -0.40
     Bio
    -0.39
    POSITIVE LOGITS
     inactivity
    0.90
     sedentary
    0.86
     idleness
    0.82
     stagn
    0.80
     immobile
    0.79
     idle
    0.79
    躇
    0.77
    SourceChecksum
    0.75
     inactive
    0.74
     stagnation
    0.73
    Activations Density 0.349%

    No Known Activations