© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8310
    Prev
    Next
    INDEX
    Explanations

    references to "crack," particularly in the context of substance use or damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     B
    -0.68
     P
    -0.67
     M
    -0.67
     
    -0.67
     D
    -0.63
     E
    -0.63
     or
    -0.63
     S
    -0.62
     L
    -0.61
     "
    -0.61
    POSITIVE LOGITS
     crack
    1.35
     Anſ
    1.34
     myſelf
    1.32
    crack
    1.32
     photolibrary
    1.28
     cracks
    1.28
     doubtnut
    1.27
     CRACK
    1.26
     Cracking
    1.24
     Reſ
    1.23
    Activations Density 0.085%

    No Known Activations