© 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. 17-GEMMASCOPE-RES-16K
    6. 38
    Prev
    Next
    INDEX
    Explanations

    medical terms related to survival rates and treatment efficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <thead>
    -0.55
    SerializedName
    -0.54
    之力
    -0.50
     trace
    -0.47
     traces
    -0.45
     Din
    -0.45
     Galbraith
    -0.45
    din
    -0.45
    Notae
    -0.43
    smo
    -0.42
    POSITIVE LOGITS
     longevity
    1.53
     Longevity
    1.20
     lifespan
    1.19
     prolong
    1.10
    寿命
    1.04
     longe
    1.03
    ongevity
    0.98
     longest
    0.98
     life
    0.96
    壽
    0.96
    Activations Density 0.329%

    No Known Activations