© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8980
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of drug or therapy related to disease treatment

    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
    expandindo
    -1.04
    .*")]
    -0.87
     doInBackground
    -0.82
    CloseOperation
    -0.78
     useAppContext
    -0.78
     وتسجيلات
    -0.75
    Приятного
    -0.74
     مشين
    -0.74
    Hozzáférés
    -0.73
     виправивши
    -0.71
    POSITIVE LOGITS
    ib
    0.90
    IB
    0.76
     Open
    0.63
     Virtual
    0.62
    Virtual
    0.61
    etti
    0.59
     virtual
    0.58
     A
    0.56
     M
    0.55
     pieces
    0.54
    Activations Density 0.124%

    No Known Activations