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. 11611
    Prev
    Next
    INDEX
    Explanations

    words related to familial relationships and emotions

    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
    AxisAlignment
    -0.95
    ')],
    -0.90
     genomen
    -0.77
    ']],
    -0.73
     vermag
    -0.73
    "),
    
    -0.73
    )"),
    -0.71
     såsom
    -0.70
     gedurende
    -0.69
    /−
    -0.69
    POSITIVE LOGITS
     stuff
    0.97
     everybody
    0.93
     scared
    0.88
     fucking
    0.87
     goddamn
    0.86
     freakin
    0.84
    everybody
    0.83
     stupid
    0.82
    Everybody
    0.82
     freaking
    0.81
    Activations Density 1.101%

    No Known Activations