Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53343
    Prev
    Next
    INDEX
    Explanations

    warnings and cautions related to medication use, particularly regarding methadone and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mental incapacitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.57
    ப்பட்டது
    -0.56
     tắc
    -0.56
    oneph
    -0.56
    ProgressHUD
    -0.54
    timewa
    -0.53
    hikari
    -0.51
    ajin
    -0.50
    ništ
    -0.50
    Initializer
    -0.49
    POSITIVE LOGITS
     препратки
    0.62
     involunt
    0.62
     Superhost
    0.59
     hallucinations
    0.57
     delirium
    0.57
     uncontrol
    0.56
     involuntarily
    0.56
    </thead>
    0.52
     incoherent
    0.52
     psychosis
    0.51
    Activations Density 0.136%

    No Known Activations