© 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. 2-GEMMASCOPE-RES-16K
    11. 1878
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical trials and drug development processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.73
    interopRequire
    -0.65
    AnchorStyles
    -0.64
    NOPQRST
    -0.61
     FetchType
    -0.60
    (!__
    -0.59
    下载附件
    -0.59
    '}),
    -0.59
    icanos
    -0.58
    MemoryWarning
    -0.58
    POSITIVE LOGITS
     trials
    0.88
     prototypes
    0.87
     experiments
    0.84
     prototype
    0.81
     Trials
    0.80
     trial
    0.80
     testing
    0.79
     Tested
    0.79
     tested
    0.78
     Trial
    0.77
    Activations Density 1.224%

    No Known Activations